© 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. 14268
    Prev
    Next
    INDEX
    Explanations

    systolic

    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
    ماية
    -0.48
    idł
    -0.48
     "
    -0.46
     compensation
    -0.45
    <eos>
    -0.45
     a
    -0.43
     the
    -0.43
    referenced
    -0.41
    百度
    -0.41
    reciated
    -0.40
    POSITIVE LOGITS
    enumi
    0.97
    ValueStyle
    0.79
    CloseOperation
    0.72
     BoxDecoration
    0.71
    extAlignment
    0.71
     صوتيه
    0.68
    tvguidetime
    0.66
    .³
    0.66
     DriverManager
    0.66
    detectChanges
    0.63
    Activations Density 0.143%

    No Known Activations