© 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. 14926
    Prev
    Next
    INDEX
    Explanations

    garrison

    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
     garrison
    -1.20
     Garrison
    -0.57
    ]));
    -0.46
    SOUNDBITE
    -0.46
     beginnetje
    -0.45
    #
    -0.44
    Viited
    -0.44
    fromCharCode
    -0.43
     giác
    -0.42
    audiovisuel
    -0.41
    POSITIVE LOGITS
    ed
    1.12
    naires
    0.82
    able
    0.63
    ned
    0.62
    Personendaten
    0.61
    aed
    0.60
    istered
    0.60
    ian
    0.60
    ierte
    0.60
    UrlResolution
    0.59
    Activations Density 0.005%

    No Known Activations