© 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. 14589
    Prev
    Next
    INDEX
    Explanations

    psychology

    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
    <bos>
    -0.68
    GEBURTSDATUM
    -0.51
     vicenda
    -0.50
     Halen
    -0.49
    一名
    -0.49
    ığınız
    -0.48
    mities
    -0.48
    bewerken
    -0.47
    cuterie
    -0.47
     саны
    -0.46
    POSITIVE LOGITS
    CSP
    0.61
     FMI
    0.57
     виправивши
    0.54
     Signalez
    0.54
    })`
    0.53
     /*#__
    0.52
     CSP
    0.52
    ftagPool
    0.51
     SDP
    0.51
    ########.
    0.51
    Activations Density 0.098%

    No Known Activations