© 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. 91199
    Prev
    Next
    INDEX
    Explanations

    anth

    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
    ModelAdmin
    -0.65
    er
    -0.63
     chip
    -0.60
     AV
    -0.57
    dement
    -0.56
     kp
    -0.52
    CHOICES
    -0.52
     sou
    -0.51
     amp
    -0.51
    django
    -0.50
    POSITIVE LOGITS
    BeginContext
    0.60
    izoen
    0.49
    üyada
    0.49
     aveug
    0.49
     Egli
    0.48
    ohyd
    0.47
    liothè
    0.46
    śmy
    0.45
    WriteBarrier
    0.45
    acy
    0.45
    Activations Density 0.158%

    No Known Activations