© 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. 91459
    Prev
    Next
    INDEX
    Explanations

    physical descriptions

    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
     dilatation
    -0.60
     berea
    -0.60
    themselves
    -0.59
     UIAlert
    -0.59
    yntaxException
    -0.59
    astéro
    -0.56
    HasBeenSet
    -0.56
    ApiOperation
    -0.55
     volant
    -0.54
    cyd
    -0.54
    POSITIVE LOGITS
    ագրություններ
    0.53
    mybatisplus
    0.47
     Audiodateien
    0.45
    +:+
    0.45
    出版年
    0.44
    طقة
    0.42
     فريبيس
    0.40
     located
    0.40
     juges
    0.40
     that
    0.38
    Activations Density 0.002%

    No Known Activations