© 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. 0-CLT-HP
    7. 93058
    Prev
    Next
    INDEX
    Explanations

    approx

    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
    fa
    -0.72
    eg
    -0.70
    kal
    -0.52
    in
    -0.47
    pon
    -0.45
    ,
    -0.43
     like
    -0.42
    icker
    -0.40
     segn
    -0.40
    on
    -0.40
    POSITIVE LOGITS
     تضيفلها
    1.05
    StructEnd
    0.99
    OGND
    0.96
    VERTISEMENT
    0.93
    ſelves
    0.92
     Efq
    0.92
    IBLIO
    0.90
     estekak
    0.90
    extAlignment
    0.87
    +:+
    0.85
    Activations Density 0.351%

    No Known Activations