© 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. 91930
    Prev
    Next
    INDEX
    Explanations

    technical/emergency situations

    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
     Compromise
    -0.78
    存于互联网档案馆
    -0.77
     poffe
    -0.75
    
    -0.75
     onPostExecute
    -0.74
     Efq
    -0.74
     selfishness
    -0.73
    ngdoc
    -0.73
     superstition
    -0.71
     Theſe
    -0.70
    POSITIVE LOGITS
     in
    0.67
     of
    0.57
    ,
    0.50
    itern
    0.48
     at
    0.48
     he
    0.47
     et
    0.47
     here
    0.46
     I
    0.46
     she
    0.46
    Activations Density 0.082%

    No Known Activations