© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10942
    Prev
    Next
    INDEX
    Explanations

    )

    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
    dymyr
    -0.68
    tagHelperRunner
    -0.66
    })));
    -0.64
    =$?
    -0.57
    \{\\
    -0.53
     dévelo
    -0.53
    ))));
    -0.53
     quelcon
    -0.52
     épais
    -0.52
    AccessorTable
    -0.52
    POSITIVE LOGITS
    @[+][
    0.53
    '
    0.50
     fortune
    0.48
     Chwiliwch
    0.47
     lay
    0.47
    upported
    0.46
     trades
    0.46
    glieder
    0.45
     and
    0.45
     habit
    0.45
    Activations Density 0.039%

    No Known Activations