© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92492
    Prev
    Next
    INDEX
    Explanations

    error handling

    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
     catch
    -0.84
    igshid
    -0.75
    CATCH
    -0.73
     catches
    -0.66
     catching
    -0.63
     himſelf
    -0.59
    elemField
    -0.58
     caught
    -0.57
    rungsseite
    -0.57
     fucks
    -0.56
    POSITIVE LOGITS
    <bos>
    0.56
    picked
    0.53
    schuh
    0.53
    ział
    0.52
    picking
    0.52
    ArrowToggle
    0.52
    DebuggerStep
    0.52
    ActionPerformed
    0.51
    poran
    0.51
     PLWABN
    0.50
    Activations Density 0.070%

    No Known Activations