© 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. 11547
    Prev
    Next
    INDEX
    Explanations

    reading

    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
     reading
    -0.55
    sendRedirect
    -0.47
     learning
    -0.46
    >//
    -0.46
    ddot
    -0.46
    ngOnDestroy
    -0.46
     ';
    -0.45
     Reading
    -0.44
    zeera
    -0.44
    ffeine
    -0.44
    POSITIVE LOGITS
    sidemargin
    0.85
    IsMutable
    0.79
    XmlAccessType
    0.77
    JspWriter
    0.76
    enumi
    0.74
    RetentionPolicy
    0.68
    帖最后由
    0.66
    LayoutStyle
    0.65
     fieldNum
    0.65
     of
    0.63
    Activations Density 0.022%

    No Known Activations