© 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. 43209
    Prev
    Next
    INDEX
    Explanations

    keep

    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
     betweenstory
    -0.76
     Paglinawan
    -0.75
    keeps
    -0.67
     politiet
    -0.66
     noastre
    -0.63
     emozioni
    -0.63
    trzyma
    -0.61
     acquittal
    -0.60
    codable
    -0.59
     Keeps
    -0.59
    POSITIVE LOGITS
     snippetHide
    0.48
    EndTag
    0.47
     reading
    0.47
     calling
    0.42
     tré
    0.41
     comfortable
    0.41
     extr
    0.40
     investing
    0.40
    
    0.40
     discovering
    0.39
    Activations Density 1.408%

    No Known Activations