© 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. 94491
    Prev
    Next
    INDEX
    Explanations

    Scientific texts

    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
     sper
    -0.57
    /**
    -0.52
    unhofer
    -0.50
    en
    -0.48
    ci
    -0.48
     enough
    -0.48
    ch
    -0.47
     forage
    -0.44
     bullets
    -0.42
    zus
    -0.42
    POSITIVE LOGITS
     ComVisible
    0.86
     kaynağından
    0.84
    XmlType
    0.74
     محفوظة
    0.73
    setVerticalGroup
    0.70
     समीक्षाओं
    0.67
    iados
    0.66
    ]^{-
    0.65
    ContentAsync
    0.64
    })->
    0.64
    Activations Density 0.038%

    No Known Activations