© 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. 43400
    Prev
    Next
    INDEX
    Explanations

    psycho

    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
    less
    -0.60
    phazard
    -0.50
    acy
    -0.48
    andom
    -0.48
    pinos
    -0.47
    amani
    -0.47
    UNIDENTIFIED
    -0.46
    NORM
    -0.45
     indepen
    -0.45
     independent
    -0.45
    POSITIVE LOGITS
    stdc
    0.71
    tableFuture
    0.71
    MENAFN
    0.69
    findpost
    0.69
     NavController
    0.68
    ollectionView
    0.63
    }))
    0.62
     fausse
    0.61
     Bantu
    0.60
     Superhost
    0.57
    Activations Density 0.251%

    No Known Activations