© 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. 1-CLT-HP
    7. 14613
    Prev
    Next
    INDEX
    Explanations

    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
     rotational
    -1.01
     ROT
    -0.96
     rotate
    -0.95
     rotation
    -0.95
     rotated
    -0.94
     Rot
    -0.93
    Rot
    -0.90
     rotations
    -0.90
    rot
    -0.89
     rotates
    -0.88
    POSITIVE LOGITS
    sty
    0.48
    SequentialGroup
    0.46
    arXiv
    0.44
     brain
    0.44
     vill
    0.43
    Ub
    0.42
    ácara
    0.42
    Carey
    0.41
    TLC
    0.41
    Biografie
    0.40
    Activations Density 0.041%

    No Known Activations