© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5764
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ArgsConstructor
    -0.73
    Disliked
    -0.56
     tetrachloride
    -0.47
    hoeddwyd
    -0.47
    AnimationsModule
    -0.46
    zeera
    -0.45
    iyi
    -0.44
     reCAPTCHA
    -0.43
     Yn
    -0.43
    jual
    -0.43
    POSITIVE LOGITS
    IsPostBack
    0.57
    m
    0.55
     oignons
    0.53
    agon
    0.53
    کز
    0.52
     للمعارف
    0.51
    buster
    0.51
    uce
    0.50
    AGON
    0.50
    au
    0.50
    Activations Density 0.009%

    No Known Activations