© 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. 0-CLT-HP
    7. 42931
    Prev
    Next
    INDEX
    Explanations

    vehicles

    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
     hábit
    -0.51
    VersionUID
    -0.50
     Area
    -0.48
     []).
    -0.48
     Iron
    -0.47
     iron
    -0.45
    tof
    -0.44
     Island
    -0.42
    _'.$
    -0.42
    _'+
    -0.42
    POSITIVE LOGITS
    ’
    0.66
    '
    0.65
     faucets
    0.64
     nahilalakip
    0.63
     scales
    0.62
    jazdu
    0.62
     berdua
    0.62
     Audiodateien
    0.61
     registers
    0.59
     indexes
    0.59
    Activations Density 0.127%

    No Known Activations