© 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. 0-CLT-HP
    7. 40169
    Prev
    Next
    INDEX
    Explanations

    add/more

    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
    by
    -0.47
    Lugar
    -0.46
    add
    -0.44
    gwt
    -0.43
     Sardegna
    -0.43
    ly
    -0.42
     mede
    -0.42
     filo
    -0.42
    minHeight
    -0.42
     میشود
    -0.40
    POSITIVE LOGITS
    MessageTagHelper
    0.94
    uxxxx
    0.93
     mergeFrom
    0.80
     '{@
    0.76
    AddTagHelper
    0.75
    RTEE
    0.75
    "])
    0.74
    TagMode
    0.74
    клопе
    0.72
     }}"></
    0.72
    Activations Density 0.025%

    No Known Activations