© 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. 4-CLT-HP
    7. 426
    Prev
    Next
    INDEX
    Explanations

    at

    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
    uxxxx
    -0.78
    NameInMap
    -0.69
    存于互联网档案馆
    -0.68
    mobileqq
    -0.68
     esternos
    -0.64
     Wikidata
    -0.59
    utilisons
    -0.57
    chitis
    -0.56
    })->
    -0.56
    Vidite
    -0.56
    POSITIVE LOGITS
     risk
    0.93
     riesgo
    0.70
     risks
    0.68
     Risk
    0.68
    Risk
    0.67
    risk
    0.64
     RISK
    0.63
     risky
    0.62
     danger
    0.59
    -
    0.59
    Activations Density 0.003%

    No Known Activations