© 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. 4-CLT-HP
    7. 3290
    Prev
    Next
    INDEX
    Explanations

    from

    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
    ніципа
    -0.54
    みな
    -0.49
     başlad
    -0.49
     simultaneous
    -0.47
    henswürdigkeiten
    -0.47
    MessageTagHelper
    -0.46
    Bigr
    -0.45
     distritos
    -0.45
    FirstResponder
    -0.45
     him
    -0.44
    POSITIVE LOGITS
    DrawerToggle
    0.63
    windowFixed
    0.58
     linkovi
    0.57
     ISNI
    0.57
    WEBPACK
    0.56
     AttributeSet
    0.55
     Australie
    0.54
    resave
    0.53
     ear
    0.53
     RouterModule
    0.53
    Activations Density 0.003%

    No Known Activations