© 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. 42647
    Prev
    Next
    INDEX
    Explanations

    wrong happening

    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
    Autoritní
    -0.98
     houſe
    -0.90
     Houſe
    -0.84
     nôtre
    -0.84
     ſind
    -0.81
     Reſ
    -0.81
     Anſ
    -0.80
     ſche
    -0.79
     pleaſure
    -0.79
     occaf
    -0.77
    POSITIVE LOGITS
     with
    0.81
     at
    0.57
     -
    0.56
    :
    0.55
     With
    0.53
     in
    0.48
    in
    0.47
     to
    0.46
    With
    0.46
     (
    0.45
    Activations Density 0.113%

    No Known Activations