© 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. 1-CLT-HP
    7. 10726
    Prev
    Next
    INDEX
    Explanations

    new

    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
    tvguidetime
    -0.64
    newly
    -0.59
     new
    -0.56
     newly
    -0.56
    Newly
    -0.52
     препратки
    -0.50
     exclamation
    -0.50
     vervol
    -0.49
    CESO
    -0.48
    guilty
    -0.48
    POSITIVE LOGITS
    ValueStyle
    0.77
    SourceChecksum
    0.59
    省市镇
    0.57
     construction
    0.56
    ⓧ
    0.56
    eriks
    0.54
    truction
    0.54
     onCreateView
    0.53
    el
    0.51
    als
    0.51
    Activations Density 0.030%

    No Known Activations