© 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. 1-CLT-HP
    7. 9033
    Prev
    Next
    INDEX
    Explanations

    league

    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
    UnitTesting
    -0.69
    ForValue
    -0.68
    UIControlState
    -0.65
     Réponses
    -0.65
    UnknownFieldSet
    -0.63
    èdia
    -0.61
    medriver
    -0.61
    ]-->
    -0.60
    Datuak
    -0.59
    #
    -0.58
    POSITIVE LOGITS
    rätt
    0.54
    jména
    0.54
    Externé
    0.54
    botten
    0.52
     clínicos
    0.51
     prisonniers
    0.50
     antaranya
    0.50
     vetro
    0.50
    ばら
    0.48
     käs
    0.47
    Activations Density 0.033%

    No Known Activations