© 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. 5-CLT-HP
    7. 4469
    Prev
    Next
    INDEX
    Explanations

    prompt

    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
    principalColumn
    -0.63
    sizeCache
    -0.61
     gynnwys
    -0.60
    KURZBESCHREIBUNG
    -0.59
    styleType
    -0.59
     transfieras
    -0.57
    gól
    -0.55
    XmlAccessType
    -0.54
     compla
    -0.53
     الحره
    -0.52
    POSITIVE LOGITS
     for
    0.66
    poved
    0.55
    帖最后由
    0.48
     vérit
    0.48
     with
    0.47
    ing
    0.47
    ktop
    0.46
    for
    0.45
    EEC
    0.45
     băr
    0.45
    Activations Density 0.001%

    No Known Activations