© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7389
    Prev
    Next
    INDEX
    Explanations

    text related to the tone of a statement or text

    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
    517
    +0.17
    0.7%
    1023
    +0.16
    0.7%
    1323
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    517
    +0.17
    0.02
    1023
    +0.16
    0.02
    1363
    +0.15
    0.02
    Negative Logits
     Cartes
    -0.50
     fumo
    -0.48
     rapi
    -0.46
    elta
    -0.46
    lanca
    -0.45
    Kích
    -0.45
    vario
    -0.43
    rure
    -0.43
     sement
    -0.42
     umbro
    -0.41
    POSITIVE LOGITS
     tone
    1.12
     Tone
    1.08
    Tone
    1.07
     Ton
    1.06
     pymysql
    1.02
     ton
    1.00
     tones
    1.00
     Tones
    0.98
    Ton
    0.97
     TON
    0.95
    Activations Density 0.088%

    No Known Activations