© 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. 45042
    Prev
    Next
    INDEX
    Explanations

    Technical documentation/Medical texts

    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
    ado
    -0.57
    aven
    -0.57
    pts
    -0.50
    avanje
    -0.50
     postIndex
    -0.50
     fore
    -0.47
    ada
    -0.47
    nal
    -0.47
    idon
    -0.47
    commune
    -0.45
    POSITIVE LOGITS
     contextLoads
    0.69
    djangoproject
    0.66
    AnimationsModule
    0.64
     FetchType
    0.60
    yaret
    0.57
    ImageContext
    0.56
    JsonKey
    0.56
     PLWABN
    0.55
    miel
    0.54
    anganronpa
    0.54
    Activations Density 0.443%

    No Known Activations