© 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. 1-CLT-HP
    7. 12153
    Prev
    Next
    INDEX
    Explanations

    explosive

    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
    __":
    -0.68
    fromCharCode
    -0.65
    eces
    -0.63
     prévue
    -0.60
    OOTDTY
    -0.60
    =$?
    -0.59
    diffusion
    -0.57
     iprot
    -0.57
    dasarkan
    -0.55
    — 
    -0.55
    POSITIVE LOGITS
    uly
    0.56
     مشين
    0.52
    Espèce
    0.52
    ity
    0.50
    ly
    0.50
    uled
    0.49
    ily
    0.48
    issage
    0.48
    MigrationBuilder
    0.47
    ary
    0.47
    Activations Density 0.020%

    No Known Activations