© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 591
    Prev
    Next
    INDEX
    Explanations

    Reuters

    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
    BURGH
    -1.63
    WireFormatLite
    -0.87
    AccessorTable
    -0.85
    ंदीखरीदारी
    -0.81
    burgh
    -0.77
    IndentedString
    -0.76
    IsMutable
    -0.74
    UrlResolution
    -0.73
     خارجية
    -0.71
    onAttach
    -0.71
    POSITIVE LOGITS
     acuer
    0.38
     r
    0.37
    RO
    0.36
    RE
    0.35
     PA
    0.35
     decisione
    0.35
    R
    0.35
    ER
    0.34
    r
    0.34
     POST
    0.34
    Activations Density 0.002%

    No Known Activations