© 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. 1-CLT-HP
    7. 9812
    Prev
    Next
    INDEX
    Explanations

    cher

    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
     Pingback
    -0.60
     bandeira
    -0.56
    endphp
    -0.53
     genoux
    -0.52
     näm
    -0.50
    coltà
    -0.49
     têtes
    -0.49
     touristes
    -0.47
     متعلقه
    -0.47
     pageContext
    -0.47
    POSITIVE LOGITS
    hound
    0.57
     loob
    0.57
     gata
    0.56
    TypedDataSet
    0.56
    ÁT
    0.53
    pano
    0.52
    obe
    0.52
    げて
    0.50
     châ
    0.50
     चीज़ों
    0.49
    Activations Density 0.197%

    No Known Activations