© 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. 0-CLT-HP
    7. 93959
    Prev
    Next
    INDEX
    Explanations

    Ingredients

    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
     Communauté
    -0.54
     ſch
    -0.51
     eſt
    -0.50
     juſ
    -0.49
     verſ
    -0.48
     ſal
    -0.47
     geſ
    -0.46
     ſche
    -0.46
     Moscou
    -0.44
     miſ
    -0.44
    POSITIVE LOGITS
    AccessorTable
    0.69
    ValueStyle
    0.67
    ⓧ
    0.63
    <bos>
    0.59
    IsContent
    0.57
    enumi
    0.56
     Leg
    0.56
    GOTREF
    0.56
     Liver
    0.54
    principalColumn
    0.54
    Activations Density 0.435%

    No Known Activations