© 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. 10061
    Prev
    Next
    INDEX
    Explanations

    Jord/Jordan/Lorde

    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
     Jord
    -0.82
    Jord
    -0.75
    djangoproject
    -0.59
     Signalez
    -0.55
    elaar
    -0.51
    Recorder
    -0.50
     beginnetje
    -0.49
    recorder
    -0.49
     blasts
    -0.49
    dimethy
    -0.47
    POSITIVE LOGITS
    y
    0.70
    enumi
    0.62
    UrlResolution
    0.57
    SequentialGroup
    0.50
     Administrativna
    0.49
    таратура
    0.48
    extAlignment
    0.47
    yn
    0.47
    gub
    0.46
    fetchone
    0.46
    Activations Density 0.204%

    No Known Activations