© 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. 76342
    Prev
    Next
    INDEX
    Explanations

    groove

    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
     followed
    -1.34
     Followed
    -1.13
    followed
    -1.13
     accompanied
    -1.05
    Followed
    -1.01
     supplemented
    -0.98
     complemented
    -0.93
     assisted
    -0.92
     replaced
    -0.91
     seguido
    -0.86
    POSITIVE LOGITS
     is
    0.75
     was
    0.55
    ErrUnexpectedEOF
    0.51
     dụ
    0.47
    expandindo
    0.45
     být
    0.45
    hardy
    0.45
    тивний
    0.44
     are
    0.43
     been
    0.43
    Activations Density 0.002%

    No Known Activations