© 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. 97568
    Prev
    Next
    INDEX
    Explanations

    Torah

    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
    lizes
    -0.57
    ularity
    -0.55
    InitVars
    -0.53
    <bos>
    -0.52
    IsPostBack
    -0.52
     StatefulWidget
    -0.52
    BASEPATH
    -0.51
    opsida
    -0.51
    alisme
    -0.51
    cityName
    -0.50
    POSITIVE LOGITS
     समीक्षक
    0.52
     JST
    0.49
    shell
    0.47
    Autoritní
    0.47
    revel
    0.47
    AddHtmlAttribute
    0.44
     particulières
    0.43
    +#+
    0.42
     SHELL
    0.42
     couche
    0.41
    Activations Density 0.000%

    No Known Activations