© 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. 15561
    Prev
    Next
    INDEX
    Explanations

    absorb

    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
     חיצוניים
    -0.88
    twimg
    -0.73
    transQ
    -0.71
    orsese
    -0.71
     enfans
    -0.71
     publicitaires
    -0.71
     cherchés
    -0.71
    addPreferredGap
    -0.70
     absorb
    -0.70
     absorción
    -0.69
    POSITIVE LOGITS
    <bos>
    0.54
     circu
    0.44
    q
    0.44
    cc
    0.41
    ers
    0.41
     Biographie
    0.41
     eggs
    0.40
    len
    0.40
    writeField
    0.40
    flex
    0.39
    Activations Density 0.022%

    No Known Activations