© 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. 5-CLT-HP
    7. 3427
    Prev
    Next
    INDEX
    Explanations

    computer hardware/software

    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
    ViewFeatures
    -0.67
    :✨
    -0.57
    MENAFN
    -0.54
     للاسماء
    -0.45
    ReusableCell
    -0.44
    ISODE
    -0.42
     vya
    -0.42
    soort
    -0.42
     Unito
    -0.41
    béco
    -0.40
    POSITIVE LOGITS
    rawDesc
    0.79
    Carriera
    0.65
    Referencer
    0.60
    CharSequence
    0.56
    counter
    0.55
    EndContext
    0.54
    grading
    0.52
    indir
    0.51
    gauge
    0.51
    copper
    0.50
    Activations Density 0.001%

    No Known Activations