© 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. 20-CLT-HP
    7. 77209
    Prev
    Next
    INDEX
    Explanations

    computer code/documentation

    np_max-act-logits · 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
    RTEE
    -1.00
    GEBURTSDATUM
    -0.89
    parsedMessage
    -0.88
    SourceChecksum
    -0.83
    UnusedPrivate
    -0.81
     transférez
    -0.81
     дописавши
    -0.81
     noDo
    -0.81
    LookAnd
    -0.80
    Autoritní
    -0.80
    POSITIVE LOGITS
     at
    1.26
     At
    0.76
     of
    0.63
    At
    0.63
    at
    0.61
     AT
    0.50
     	e
    0.46
    AtIndex
    0.44
     bij
    0.44
     by
    0.43
    Activations Density 0.000%

    No Known Activations