© 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. 92997
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific documents

    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
    illable
    -0.66
    İŞ
    -0.60
    GEBURTS
    -0.59
    ')):
    -0.57
    onded
    -0.57
    "})
    -0.57
    Notae
    -0.56
    UTERS
    -0.56
    uvwxyz
    -0.55
    Cordialement
    -0.54
    POSITIVE LOGITS
    DockStyle
    0.68
     Only
    0.65
    Only
    0.63
    SourceChecksum
    0.55
     Spending
    0.52
    Most
    0.51
     Most
    0.51
     Many
    0.50
     Dogs
    0.50
    only
    0.49
    Activations Density 0.000%

    No Known Activations