© 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. 38724
    Prev
    Next
    INDEX
    Explanations

    phenomenal

    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
    DebuggerNonUser
    -0.56
    crumbs
    -0.55
     plausible
    -0.52
    IsContent
    -0.51
    ="{{$
    -0.51
     besieged
    -0.51
     pawn
    -0.50
     Consultado
    -0.49
    bnf
    -0.49
     Total
    -0.49
    POSITIVE LOGITS
     autorytatywna
    0.68
    Xna
    0.66
     <<<<<<<<<<<<<<
    0.59
    ing
    0.59
     Efq
    0.59
     raiſ
    0.58
     houſe
    0.57
    تقاوى
    0.56
     myſelf
    0.56
     firent
    0.55
    Activations Density 0.124%

    No Known Activations