© 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. 5-CLT-HP
    7. 5094
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    findpost
    -0.80
    RenderAtEndOf
    -0.76
    ArgsConstructor
    -0.71
     Normdatei
    -0.70
    出版年
    -0.68
    ⓧ
    -0.68
    الحياه
    -0.68
     ivelany
    -0.65
    __":
    -0.64
     utafitiHapana
    -0.59
    POSITIVE LOGITS
     used
    0.48
     defaultstate
    0.42
     consulted
    0.39
    minipage
    0.38
     lau
    0.38
     owed
    0.36
    Przypisy
    0.35
     azul
    0.35
     asp
    0.35
     shown
    0.33
    Activations Density 0.001%

    No Known Activations