© 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. 94605
    Prev
    Next
    INDEX
    Explanations

    features and modifications

    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
     attached
    -0.99
    attached
    -0.96
    Attached
    -0.87
     Attached
    -0.84
     inserted
    -0.81
     appended
    -0.76
     equipped
    -0.72
     enclosed
    -0.71
    equipped
    -0.71
     positioned
    -0.71
    POSITIVE LOGITS
    ContentLoaded
    0.54
    gleiche
    0.52
    itie
    0.52
     khảo
    0.47
    ukkah
    0.47
     LIE
    0.47
     rank
    0.46
    ggish
    0.45
    nij
    0.45
    ocument
    0.45
    Activations Density 0.404%

    No Known Activations