© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 5558
    Prev
    Next
    INDEX
    Explanations

    Chrysler

    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
    ParallelGroup
    -0.80
     GenerationType
    -0.69
    jsxFileName
    -0.61
    кипедия
    -0.60
    URLException
    -0.60
    classnames
    -0.60
     FetchType
    -0.59
    fieldLabel
    -0.59
    providedIn
    -0.59
    VolleyError
    -0.59
    POSITIVE LOGITS
    Ch
    0.52
    chon
    0.52
    CR
    0.51
     Ch
    0.50
    CHR
    0.48
     ch
    0.47
     AG
    0.47
     CR
    0.46
     frères
    0.45
    elastic
    0.45
    Activations Density 0.004%

    No Known Activations