© 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. 10255
    Prev
    Next
    INDEX
    Explanations

    cure eradicate

    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
     sanitaires
    -0.59
    __*/
    -0.57
     sanitarias
    -0.56
    webElementGuid
    -0.51
     TextAppearance
    -0.51
     coraggio
    -0.47
     ilman
    -0.46
     élevées
    -0.46
     lèvres
    -0.45
     osallist
    -0.45
    POSITIVE LOGITS
    ImageContext
    0.63
    kháu
    0.62
    loem
    0.61
    GRANTED
    0.60
    脚注の使い方
    0.60
     }{@
    0.60
    ValueStyle
    0.59
    createStatement
    0.59
    principalColumn
    0.58
    tvguidetime
    0.58
    Activations Density 0.086%

    No Known Activations