Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5950
    Prev
    Next
    INDEX
    Explanations

    proper nouns or named entities, although it also seems to have some sensitivity to titles

    oai_token-act-pair · gemini-2.0-flash

    references to charitable organizations

    np_token-act-pair-logits · gpt-4o-mini

    Project, organization, and title names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -1.15
    ,
    -1.02
     the
    -0.90
     I
    -0.88
     in
    -0.88
     to
    -0.87
     that
    -0.85
    ↵
    -0.82
     as
    -0.82
     (
    -0.81
    POSITIVE LOGITS
    expandindo
    1.54
     Efq
    1.45
     Theſe
    1.41
     itſelf
    1.35
     disambiguazione
    1.31
    <unused43>
    1.31
    <unused14>
    1.30
    <unused16>
    1.30
    <unused8>
    1.30
    <pad>
    1.30
    Activations Density 3.431%

    No Known Activations