© 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. 94582
    Prev
    Next
    INDEX
    Explanations

    Cliffs

    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
     purpoſe
    -1.00
     Majefty
    -0.98
    Билгалдахарш
    -0.97
     ſtate
    -0.96
     Efq
    -0.94
     fubject
    -0.94
    GEBURTSDATUM
    -0.92
     raiſ
    -0.91
     pleaſure
    -0.90
     houſe
    -0.90
    POSITIVE LOGITS
    ly
    0.73
     “
    0.56
     e
    0.53
     
    0.53
     (
    0.52
     Be
    0.48
     F
    0.48
     Re
    0.48
     I
    0.46
    line
    0.45
    Activations Density 0.538%

    No Known Activations