© 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. 42492
    Prev
    Next
    INDEX
    Explanations

    films

    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
    protoimpl
    -0.78
     purpoſe
    -0.71
     fubject
    -0.71
     Conſ
    -0.63
    soluble
    -0.62
     pleaſure
    -0.62
     bonds
    -0.60
     juſ
    -0.59
     auroit
    -0.59
     actualité
    -0.59
    POSITIVE LOGITS
     about
    0.58
    ően
    0.58
     of
    0.53
    kező
    0.53
    isSet
    0.49
     set
    0.47
     and
    0.47
    coring
    0.46
     to
    0.45
    :+:
    0.45
    Activations Density 0.013%

    No Known Activations