© 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. 1-CLT-HP
    7. 12502
    Prev
    Next
    INDEX
    Explanations

    language and words

    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
     himo
    -0.58
    okovic
    -0.53
    ipedi
    -0.53
     Spisak
    -0.51
     beginnetje
    -0.50
    Према
    -0.49
    covite
    -0.48
     waarop
    -0.47
     allAfrica
    -0.47
    mantec
    -0.47
    POSITIVE LOGITS
    ⓧ
    0.59
    IBOutlet
    0.56
    displayquote
    0.55
     وتسجيلات
    0.55
     MainAxisSize
    0.55
     ModelExpression
    0.53
    Clar
    0.51
    consulté
    0.49
    icke
    0.49
     InputDecoration
    0.48
    Activations Density 0.002%

    No Known Activations