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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12503
    Prev
    Next
    INDEX
    Explanations

    years/dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.69
    -
    -0.47
     or
    -0.47
    ,
    -0.46
     lapangan
    -0.41
     fjor
    -0.40
     and
    -0.39
    .
    -0.37
     to
    -0.36
    /
    -0.36
    POSITIVE LOGITS
     الحره
    1.37
     فريبيس
    1.22
     يتيمه
    1.20
     tartalomajánló
    1.15
    ArgsConstructor
    1.12
    extAlignment
    1.05
    LookAnd
    1.03
     Houſe
    1.00
    migrationBuilder
    0.99
     consultato
    0.99
    Activations Density 0.754%

    No Known Activations