© 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. 43261
    Prev
    Next
    INDEX
    Explanations

    learning

    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
    EndGlobalSection
    -0.59
    ArrowToggle
    -0.53
    Losing
    -0.52
    ffindor
    -0.51
     des
    -0.50
    /**
    -0.48
    Gön
    -0.47
    covite
    -0.46
    turnstile
    -0.46
    комо
    -0.45
    POSITIVE LOGITS
     pédagog
    0.66
     suaminya
    0.58
    InSection
    0.55
     utafitiHapana
    0.54
     marquées
    0.54
     réguli
    0.54
     scolaires
    0.54
     sélectionnés
    0.53
     istrinya
    0.53
    Delight
    0.53
    Activations Density 0.245%

    No Known Activations