© 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. 4693
    Prev
    Next
    INDEX
    Explanations

    chemistry/scientific articles

    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
     समीक्षाओं
    -0.69
    aarrggbb
    -0.69
    ContentAsync
    -0.69
     avoient
    -0.68
    abestanden
    -0.68
     feroit
    -0.67
    Personensuche
    -0.66
     auroit
    -0.66
     Theſe
    -0.66
     vägen
    -0.65
    POSITIVE LOGITS
    favicon
    0.49
    ]=>
    0.46
     GNA
    0.42
     verv
    0.42
    ICOS
    0.41
     furnishings
    0.40
     grains
    0.40
     Ubicación
    0.39
     issues
    0.39
    ellingham
    0.38
    Activations Density 0.001%

    No Known Activations