© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5970
    Prev
    Next
    INDEX
    Explanations

    authority figures/sources/investigation

    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
    hode
    -0.55
    GEBURTS
    -0.52
     <<<<<<<<<<<<<<
    -0.49
    帖最后由
    -0.48
     ब्रेकडाउन
    -0.47
     defaultstate
    -0.47
    tem
    -0.47
     sentirse
    -0.47
    trib
    -0.46
    ieme
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.73
    WindowConstants
    0.64
     say
    0.52
     claim
    0.52
    ]();
    0.51
     RSSSF
    0.50
     have
    0.50
    Filmographie
    0.49
    varlak
    0.47
    Filmografie
    0.46
    Activations Density 0.001%

    No Known Activations