© 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. 15735
    Prev
    Next
    INDEX
    Explanations

    errors/issues

    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
    WriteTagHelper
    -0.96
    RenderAtEndOf
    -0.85
    ArgsConstructor
    -0.85
    findpost
    -0.81
    +#+#
    -0.76
    WebServlet
    -0.74
    ValueStyle
    -0.71
     चीज़ों
    -0.70
    setVerticalGroup
    -0.69
     ErrInvalid
    -0.69
    POSITIVE LOGITS
     filling
    0.42
    filling
    0.42
    ’
    0.41
     card
    0.39
     gu
    0.37
    Brains
    0.36
    ])):
    0.36
    mine
    0.36
     floor
    0.36
     él
    0.36
    Activations Density 0.016%

    No Known Activations