© 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. 94225
    Prev
    Next
    INDEX
    Explanations

    create

    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
     AssemblyCulture
    -0.63
    Jeografia
    -0.60
     ketahui
    -0.57
    ochial
    -0.52
     esternos
    -0.52
    WriteTagHelper
    -0.51
    ">//
    -0.50
    تقاوى
    -0.50
    İstinadlar
    -0.49
    IntoConstraints
    -0.49
    POSITIVE LOGITS
     a
    0.66
    able
    0.64
     enough
    0.62
    Portale
    0.57
    er
    0.56
     sufficient
    0.56
    endphp
    0.55
    ée
    0.54
    rog
    0.54
     coalitions
    0.54
    Activations Density 0.065%

    No Known Activations