© 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. 91610
    Prev
    Next
    INDEX
    Explanations

    looked

    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
    :✨
    -0.60
     ModelExpression
    -0.59
     after
    -0.52
     After
    -0.50
    after
    -0.50
     /\.(
    -0.49
    newswire
    -0.47
     welfare
    -0.47
    +:+
    -0.45
    onedDateTime
    -0.45
    POSITIVE LOGITS
    TestingModule
    0.59
    zzleHttp
    0.59
    LabelTagHelper
    0.58
     malheureux
    0.58
    CodeAttribute
    0.54
    UrlEncoded
    0.53
     puzzled
    0.52
    bär
    0.52
     архивлан
    0.51
     resourceCulture
    0.51
    Activations Density 0.001%

    No Known Activations