© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5826
    Prev
    Next
    INDEX
    Explanations

    Rodeo

    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
    \{\\
    -0.88
    ImageContext
    -0.77
    Hentet
    -0.77
    InjectAttribute
    -0.66
    expandindo
    -0.64
    postIndex
    -0.64
     nakalista
    -0.63
    inį
    -0.62
    extAlignment
    -0.62
     useAppContext
    -0.61
    POSITIVE LOGITS
    endsection
    0.52
     Stahl
    0.47
     Cos
    0.45
     Sch
    0.44
     Glory
    0.44
    netinet
    0.43
     "..\..\
    0.43
    logram
    0.43
    grö
    0.42
     Com
    0.40
    Activations Density 0.000%

    No Known Activations