© 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. 5-CLT-HP
    7. 96050
    Prev
    Next
    INDEX
    Explanations

    chat/query text

    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
     feroit
    -1.07
     avoient
    -1.02
     étoient
    -1.00
     auroit
    -0.96
     auffi
    -0.95
     ainfi
    -0.94
    lapsingToolbar
    -0.93
     Efq
    -0.93
     quæ
    -0.91
     cérami
    -0.91
    POSITIVE LOGITS
    ,"
    0.72
     [
    0.70
    ,
    0.69
    ,”
    0.69
     
    0.65
    .
    0.64
     I
    0.63
    ↵
    0.63
     my
    0.61
    ",
    0.60
    Activations Density 0.004%

    No Known Activations