© 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. 14895
    Prev
    Next
    INDEX
    Explanations

    Day

    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
    nie
    -0.94
    AutoScale
    -0.48
    NIE
    -0.47
    //*[@
    -0.46
    nobody
    -0.42
     bip
    -0.41
    IsPostBack
    -0.41
     I
    -0.40
    thique
    -0.40
     up
    -0.40
    POSITIVE LOGITS
     שוליים
    0.77
    StoreMessageInfo
    0.75
    లాలు
    0.73
    CRR
    0.68
    Diweddarwch
    0.67
    </thead>
    0.64
    Datuak
    0.64
     ③
    0.63
     iconFacebook
    0.61
     crdi
    0.61
    Activations Density 0.035%

    No Known Activations