© 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. 20-CLT-HP
    7. 72922
    Prev
    Next
    INDEX
    Explanations

    code/technical documentation

    np_max-act-logits · 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
    msgSender
    -0.45
     exist
    -0.41
    FDRE
    -0.41
    /*
    -0.40
     recic
    -0.39
    exist
    -0.38
    BagConstraints
    -0.37
    淺
    -0.37
    Existing
    -0.37
    caught
    -0.37
    POSITIVE LOGITS
    
    0.71
    InjectAttribute
    0.63
    Geplaatst
    0.61
    RenderAtEndOf
    0.61
    makeConstraints
    0.61
     referenties
    0.61
     Audiodateien
    0.59
    addContainerGap
    0.57
     виправивши
    0.56
     udaler
    0.56
    Activations Density 0.001%

    No Known Activations