© 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. 1498
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes/dialogue

    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
    AndEndTag
    -0.67
    LookAnd
    -0.65
     CURIAM
    -0.59
    зулта
    -0.57
    ="">
    -0.56
    adaptiveStyles
    -0.55
     nôtre
    -0.55
     mergeFrom
    -0.54
    PointerException
    -0.54
     mourir
    -0.54
    POSITIVE LOGITS
    </u>
    0.50
    enumi
    0.48
     TextInputType
    0.48
     kasarigan
    0.45
     صوتيه
    0.45
     pstmt
    0.44
    TagHelper
    0.43
    itans
    0.43
     podjela
    0.43
    ddin
    0.42
    Activations Density 0.009%

    No Known Activations