© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7399
    Prev
    Next
    INDEX
    Explanations

    references to tabs or tabulation in a structured context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1926
    +0.16
    0.7%
    405
    +0.16
    0.7%
    1573
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1573
    +0.16
    0.02
    1926
    +0.16
    0.02
    1137
    +0.15
    0.02
    Negative Logits
     influen
    -0.53
     \<
    -0.49
     democra
    -0.48
     Managua
    -0.46
     Pizarro
    -0.46
     elems
    -0.45
     sclero
    -0.45
     Morelos
    -0.45
     Micho
    -0.45
     minValue
    -0.44
    POSITIVE LOGITS
     tab
    1.39
     Tab
    1.35
    tab
    1.27
    Tab
    1.26
     tabs
    1.18
     TAB
    1.16
    TAB
    1.14
     Tabs
    1.04
    tabs
    0.96
    Tabs
    0.94
    Activations Density 0.082%

    No Known Activations