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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3617
    Prev
    Next
    INDEX
    Explanations

    expressions related to uncertainty or speculation

    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
    1328
    +0.13
    0.4%
    481
    +0.11
    0.4%
    871
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.13
    0.08
    481
    +0.11
    0.07
    1425
    +0.11
    0.06
    Negative Logits
    IContainer
    -0.49
     Heinemann
    -0.46
    Ո
    -0.45
    spender
    -0.44
     habile
    -0.44
     Majest
    -0.41
    pug
    -0.41
     Bla
    -0.41
    ESI
    -0.41
    FailureListener
    -0.41
    POSITIVE LOGITS
     reluct
    0.94
     repug
    0.90
     perfet
    0.90
     impra
    0.89
     unwarran
    0.88
     WOULD
    0.86
     ?...
    0.86
     disagre
    0.86
     impractica
    0.83
     intersper
    0.83
    Activations Density 0.255%

    No Known Activations