© 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. 73074
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ########.
    -0.68
     disambiguazione
    -0.62
    lji
    -0.57
    writeFieldEnd
    -0.57
     heisst
    -0.53
    Hentet
    -0.52
    endfor
    -0.51
    mtrl
    -0.51
    ForTesting
    -0.50
    TypedDataSet
    -0.49
    POSITIVE LOGITS
    uxxxx
    0.70
     jotka
    0.49
    setupUi
    0.49
    IndentedString
    0.47
     Organizer
    0.47
    cèse
    0.47
    __':
    0.47
    Organized
    0.47
    __))
    0.46
    keyed
    0.46
    Activations Density 0.001%

    No Known Activations