© 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. 94348
    Prev
    Next
    INDEX
    Explanations

    coil

    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
     avoient
    -0.80
    bootstrapcdn
    -0.79
     oreilles
    -0.76
     médec
    -0.75
     étoient
    -0.73
     scolaires
    -0.73
     jambes
    -0.72
     nakalista
    -0.72
     enfans
    -0.71
     venons
    -0.71
    POSITIVE LOGITS
    aarrggbb
    0.56
    Havolalar
    0.55
     насељу
    0.55
    цездатний
    0.54
     فريبيس
    0.53
    isation
    0.53
     Fog
    0.52
     wraps
    0.52
     wrap
    0.51
     weights
    0.51
    Activations Density 0.146%

    No Known Activations