© 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. 97641
    Prev
    Next
    INDEX
    Explanations

    Code/foreign languages

    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
    simus
    -1.53
    migrationBuilder
    -0.66
    الدراسه
    -0.60
    tonsoft
    -0.60
    routeProvider
    -0.60
    modelBuilder
    -0.58
     Chwiliwch
    -0.57
    Parabéns
    -0.56
    Hãy
    -0.56
    andExpect
    -0.55
    POSITIVE LOGITS
    rungsseite
    0.63
     pory
    0.57
     fussy
    0.56
     letto
    0.52
     toga
    0.52
     Administrativna
    0.52
    xase
    0.51
     Verarbeitung
    0.51
    kenstock
    0.51
    よる
    0.49
    Activations Density 0.114%

    No Known Activations