© 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. 92756
    Prev
    Next
    INDEX
    Explanations

    scientific language, math expressions

    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
    NAH
    -0.47
    antry
    -0.44
    Stop
    -0.44
     messaging
    -0.42
    IGEN
    -0.42
    erialized
    -0.42
    исленность
    -0.41
    grond
    -0.41
     jsPsych
    -0.41
     stops
    -0.40
    POSITIVE LOGITS
    WebVitals
    0.80
    ########.
    0.70
    OGND
    0.69
    Portale
    0.61
     שוליים
    0.61
    UnusedPrivate
    0.59
    Portail
    0.59
    NameInMap
    0.59
    الإنجليزية
    0.58
    GEBURTSDATUM
    0.58
    Activations Density 0.007%

    No Known Activations