© 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. 15782
    Prev
    Next
    INDEX
    Explanations

    Tees

    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
     Gopal
    -0.51
    ValueStyle
    -0.48
    visuel
    -0.46
    SCORE
    -0.46
    POI
    -0.46
     SRA
    -0.45
     éditoriale
    -0.45
    перь
    -0.45
    sent
    -0.45
    HOUR
    -0.44
    POSITIVE LOGITS
    <?
    0.68
     OFDb
    0.60
     Audiodateien
    0.59
    MemoryWarning
    0.59
     CanadaChoose
    0.56
    __(/*!
    0.56
     vPvB
    0.56
     minority
    0.55
    Portale
    0.54
     autorytatywna
    0.53
    Activations Density 0.008%

    No Known Activations