© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96966
    Prev
    Next
    INDEX
    Explanations

    gaps

    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
    перь
    -0.43
    autant
    -0.40
     bouteille
    -0.40
    ])));
    -0.40
    ↵↵↵
    -0.39
    ").
    -0.39
    diel
    -0.38
    Continues
    -0.38
    <eos>
    -0.37
    icher
    -0.37
    POSITIVE LOGITS
     незавершена
    0.90
    tagHelperRunner
    0.85
    parsedMessage
    0.79
    حياتها
    0.79
     ModelExpression
    0.77
     Wikimedijinoj
    0.77
    Personendaten
    0.76
    JspWriter
    0.75
    WebServlet
    0.75
     defaultstate
    0.75
    Activations Density 0.006%

    No Known Activations