© 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. 15364
    Prev
    Next
    INDEX
    Explanations

    list

    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
    rrggbb
    -0.64
     Trento
    -0.59
     تضيفلها
    -0.53
    bleau
    -0.53
    List
    -0.52
     stork
    -0.51
    StructEnd
    -0.51
     Modena
    -0.50
     Brescia
    -0.50
    list
    -0.48
    POSITIVE LOGITS
    parsedMessage
    0.65
    ="">
    0.52
    "),
    0.50
    SourceChecksum
    0.49
    ")));
    0.49
     unknownFields
    0.49
     lho
    0.48
     LY
    0.47
     ($
    0.47
    пат
    0.47
    Activations Density 0.035%

    No Known Activations