© 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. 5-CLT-HP
    7. 91355
    Prev
    Next
    INDEX
    Explanations

    scientific/technical

    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
    GEBURTSDATUM
    -0.83
    extAlignment
    -0.80
    UrlResolution
    -0.66
    OGND
    -0.64
    enseignements
    -0.60
     medals
    -0.58
     passwords
    -0.58
     statuses
    -0.57
     velocities
    -0.57
     fellowships
    -0.57
    POSITIVE LOGITS
     of
    0.88
    <bos>
    0.79
    ]}>
    0.51
     between
    0.47
    cruz
    0.46
     της
    0.43
     about
    0.43
    of
    0.42
     ≥
    0.42
     supérieur
    0.42
    Activations Density 0.063%

    No Known Activations