© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 21
    Prev
    Next
    INDEX
    Explanations

    Authors

    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
    audiovisuel
    -0.38
    onces
    -0.37
    ⓧ
    -0.36
    vitis
    -0.34
    хозяй
    -0.34
     chá
    -0.33
    estina
    -0.33
    ô
    -0.33
    caching
    -0.32
     OGSÅ
    -0.31
    POSITIVE LOGITS
    DebuggerNonUser
    0.81
    ंदीखरीदारी
    0.78
    umesc
    0.69
    cedure
    0.68
    новниш
    0.66
    WireFormat
    0.65
    lloworld
    0.65
    mongoose
    0.65
     endings
    0.64
     endregion
    0.64
    Activations Density 0.011%

    No Known Activations