© 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. 0-CLT-HP
    7. 94127
    Prev
    Next
    INDEX
    Explanations

    signaling

    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
     Indication
    -1.17
     indicator
    -1.16
     indication
    -1.16
     indicate
    -1.15
    indicate
    -1.13
    indicator
    -1.10
     Indicate
    -1.10
     Indicator
    -1.08
     INDIC
    -1.06
    indication
    -1.02
    POSITIVE LOGITS
    mento
    0.60
     AssemblyCulture
    0.60
     thức
    0.51
    */)
    0.51
     энциклопедия
    0.50
    ment
    0.50
    undum
    0.49
    reten
    0.47
    OfWork
    0.47
    less
    0.47
    Activations Density 1.357%

    No Known Activations