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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3027
    Prev
    Next
    INDEX
    Explanations

    t

    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
     Roskov
    -0.94
     Pristupljeno
    -0.85
    Ehrungen
    -0.85
     يتيمه
    -0.81
    */].
    -0.78
     насељу
    -0.78
    MessageOf
    -0.77
     للمعارف
    -0.74
     FishBase
    -0.74
    DOCTYPE
    -0.73
    POSITIVE LOGITS
     curious
    0.47
     сом
    0.38
    emes
    0.36
    มิ
    0.33
     EM
    0.33
    WEBPACK
    0.33
    TEE
    0.33
    mis
    0.31
    ренко
    0.31
    ORS
    0.31
    Activations Density 0.005%

    No Known Activations