© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91991
    Prev
    Next
    INDEX
    Explanations

    damage

    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
     damage
    -1.30
     Damage
    -1.23
    damage
    -1.21
    Damage
    -1.16
     DAMAGE
    -1.10
     dégâts
    -1.03
    Personendaten
    -0.99
     damages
    -0.98
    damaged
    -0.97
     noDo
    -0.96
    POSITIVE LOGITS
    .
    0.73
    ,
    0.69
     of
    0.66
     and
    0.61
    /
    0.60
     (
    0.53
     or
    0.53
    e
    0.53
     that
    0.52
    [
    0.51
    Activations Density 0.351%

    No Known Activations