© 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. 20-CLT-HP
    7. 73612
    Prev
    Next
    INDEX
    Explanations

    Probably code or technical texts

    np_max-act-logits · 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
    aarrggbb
    -0.71
    principalColumn
    -0.62
     continúas
    -0.59
    expandindo
    -0.50
    ThroughAttribute
    -0.49
    Comté
    -0.47
    IsMutable
    -0.45
    ocry
    -0.43
    ########.
    -0.43
    arikat
    -0.43
    POSITIVE LOGITS
    MemoryWarning
    0.56
     brake
    0.55
     sh
    0.51
    èr
    0.50
    StreetMap
    0.50
     British
    0.50
    IGraphics
    0.50
    brake
    0.49
    rà
    0.48
    melse
    0.48
    Activations Density 0.000%

    No Known Activations