© 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. 42410
    Prev
    Next
    INDEX
    Explanations

    discharge

    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
    ell
    -0.86
    Geplaatst
    -0.77
     discharge
    -0.76
     hull
    -0.70
     hulls
    -0.67
     Discharge
    -0.65
    discharge
    -0.65
    المكان
    -0.65
    :✨
    -0.64
     незавершена
    -0.63
    POSITIVE LOGITS
    tvguidetime
    0.55
    parsedMessage
    0.54
    conti
    0.53
     defaultstate
    0.52
     bumbu
    0.51
    #+#
    0.48
    訊
    0.48
     términos
    0.46
     wikipagina
    0.45
     plantilla
    0.45
    Activations Density 0.114%

    No Known Activations