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. 0-CLT-HP
    4. 39169
    Prev
    Next
    INDEX
    Explanations

    bnd

    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
     Acton
    -1.59
    ricians
    -0.47
     Drapeau
    -0.47
    >%
    -0.46
    MessageOf
    -0.45
    TagMode
    -0.44
    ########.
    -0.44
    lit
    -0.44
    s
    -0.44
    ंदीखरीदारी
    -0.43
    POSITIVE LOGITS
    pulos
    0.60
    findpost
    0.59
    kmale
    0.59
    wezig
    0.57
    RBC
    0.54
    ėms
    0.54
    duled
    0.54
    elfare
    0.53
    chyma
    0.53
    ípios
    0.52
    Activations Density 0.152%

    No Known Activations