Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45325
    Prev
    Next
    INDEX
    Explanations

    architect

    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
    Autoritní
    -0.69
     Dipl
    -0.59
     Tuba
    -0.57
     tuba
    -0.56
    uxxxx
    -0.56
    UVWXYZ
    -0.54
    ViewFeatures
    -0.51
     Sins
    -0.51
    Portale
    -0.50
    quelize
    -0.50
    POSITIVE LOGITS
    出版年
    0.84
    MediaStore
    0.55
    menea
    0.53
    fortawesome
    0.51
    adpleegd
    0.50
    /***/
    0.50
    MessageOf
    0.50
    \{\\
    0.49
     {}));
    0.49
    boer
    0.49
    Activations Density 0.029%

    No Known Activations