© 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. 92114
    Prev
    Next
    INDEX
    Explanations

    text snippets

    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
    SceneManagement
    -0.71
    <bos>
    -0.67
    новниш
    -0.56
    enterOuterAlt
    -0.55
    fortawesome
    -0.54
    LElement
    -0.52
     Vikipedi
    -0.52
     EnglishChoose
    -0.50
    IGraphics
    -0.49
     Proprietary
    -0.48
    POSITIVE LOGITS
     whether
    0.57
     who
    0.56
    Einzelnachweise
    0.54
     keeping
    0.54
     our
    0.54
     people
    0.52
    httphttps
    0.49
     spalle
    0.49
    atisk
    0.49
    ]();
    0.48
    Activations Density 0.001%

    No Known Activations