© 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. 20-CLT-HP
    7. 75713
    Prev
    Next
    INDEX
    Explanations

    Film

    np_max-act-logits · 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
    شهاد
    -0.55
    matchCondition
    -0.55
    vereignty
    -0.51
    argout
    -0.48
    Przypisy
    -0.48
    ்ச
    -0.47
    value
    -0.47
    fjspx
    -0.47
    🧵
    -0.46
    source
    -0.46
    POSITIVE LOGITS
     Film
    0.56
     FILM
    0.54
     film
    0.54
     protoimpl
    0.52
    Film
    0.51
     films
    0.51
    ynb
    0.51
     Movie
    0.50
    Brainz
    0.50
     Means
    0.50
    Activations Density 0.000%

    No Known Activations