© 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. 93853
    Prev
    Next
    INDEX
    Explanations

    rack

    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
     esternos
    -0.78
     rack
    -0.77
    __":
    -0.74
    __':
    -0.73
    __':
    -0.70
     Bi
    -0.69
     Roskov
    -0.68
     racks
    -0.65
     racked
    -0.64
    __":
    -0.62
    POSITIVE LOGITS
    zuführen
    0.55
    :+:
    0.52
    ngel
    0.51
    UnitTesting
    0.50
     endangered
    0.49
    amaged
    0.48
    Hochspringen
    0.47
     defoli
    0.47
     measles
    0.47
     voix
    0.46
    Activations Density 0.070%

    No Known Activations