© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1796
    Prev
    Next
    INDEX
    Explanations

    into

    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
     nahilalakip
    -1.02
    ंदीखरीदारी
    -0.94
    tagHelperRunner
    -0.84
     يتيمه
    -0.72
    مصادر
    -0.68
    principalTable
    -0.63
    +#+#
    -0.62
    UnknownFields
    -0.62
    NegativeButton
    -0.61
    featureID
    -0.60
    POSITIVE LOGITS
     a
    0.69
     effective
    0.57
     decent
    0.55
     reasonably
    0.50
     fair
    0.48
     good
    0.48
     sizeable
    0.48
     reasonable
    0.47
     sizable
    0.47
    立派
    0.47
    Activations Density 0.039%

    No Known Activations