© 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. 5-CLT-HP
    7. 4273
    Prev
    Next
    INDEX
    Explanations

    technical/legal/mathematical texts

    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
    SourceChecksum
    -0.99
     Roskov
    -0.84
     تانيه
    -0.81
    ########.
    -0.78
    uxley
    -0.71
    DockStyle
    -0.71
    migrationBuilder
    -0.69
    GeneratedMessage
    -0.67
    Personensuche
    -0.65
     transfieras
    -0.65
    POSITIVE LOGITS
    ute
    0.63
     urbanas
    0.45
     구
    0.42
     tár
    0.41
     inter
    0.40
    uti
    0.40
    ToObject
    0.40
    िज
    0.38
    спек
    0.38
     ut
    0.37
    Activations Density 0.001%

    No Known Activations