© 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. 0-CLT-HP
    7. 43568
    Prev
    Next
    INDEX
    Explanations

    code/licenses/legal

    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
     StatefulWidget
    -0.70
     étoient
    -0.70
     magique
    -0.67
    lanzen
    -0.67
     citoy
    -0.66
     avoient
    -0.66
     vierge
    -0.65
     épic
    -0.65
    حياته
    -0.65
     polaire
    -0.64
    POSITIVE LOGITS
    CloseOperation
    0.58
     insuffisamment
    0.56
     nî
    0.52
    ⁡
    0.47
    PullParser
    0.47
     صوتيه
    0.47
    RTLI
    0.46
    audiovisuel
    0.46
    Awwww
    0.46
    ContentAlignment
    0.45
    Activations Density 1.671%

    No Known Activations