© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 1017
    Prev
    Next
    INDEX
    Explanations

    flipping/rotation

    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
     flipping
    -1.21
     flip
    -1.08
     flipped
    -1.05
     flips
    -1.03
    flip
    -0.98
     Fli
    -0.87
    Fli
    -0.86
    flipped
    -0.85
     Flip
    -0.82
    Flip
    -0.80
    POSITIVE LOGITS
     referenties
    0.64
     prière
    0.57
     Drapeau
    0.56
     imprimée
    0.55
     réfugiés
    0.54
     complémentaires
    0.54
     pitié
    0.53
    AccessException
    0.53
    GPR
    0.52
     répartition
    0.52
    Activations Density 0.032%

    No Known Activations