© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45729
    Prev
    Next
    INDEX
    Explanations

    antibiotics

    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
    romycin
    -0.84
    +:+
    -0.63
     nahilalakip
    -0.63
     émotions
    -0.61
    amycin
    -0.59
     mauvaises
    -0.58
     segni
    -0.58
     Chwiliwch
    -0.56
     positifs
    -0.55
    @[+][
    -0.55
    POSITIVE LOGITS
     Majefty
    0.60
     fathoms
    0.59
    ConstraintMaker
    0.57
    endwhile
    0.55
    PostExecute
    0.54
    ſelf
    0.52
     typelib
    0.52
    ArgsConstructor
    0.52
    matically
    0.51
    SPATH
    0.50
    Activations Density 0.194%

    No Known Activations