© 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. 9713
    Prev
    Next
    INDEX
    Explanations

    Lorenzo

    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
    SharedDtor
    -0.96
     Roskov
    -0.84
     Lorenzo
    -0.81
    abestanden
    -0.81
    enumii
    -0.79
    IndentedString
    -0.79
    ValueGeneration
    -0.77
    Portale
    -0.75
     CURLOPT
    -0.75
    featureID
    -0.70
    POSITIVE LOGITS
     (
    0.50
     covering
    0.47
    s
    0.40
     cover
    0.40
     ((
    0.38
    amem
    0.36
     status
    0.36
     conos
    0.36
    cover
    0.35
     Status
    0.35
    Activations Density 0.108%

    No Known Activations