© 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. 5930
    Prev
    Next
    INDEX
    Explanations

    scientific/technical 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
    DockStyle
    -0.51
    argout
    -0.44
    zcze
    -0.39
     cocin
    -0.39
     afterlife
    -0.38
    待
    -0.38
    readObject
    -0.37
    WebVitals
    -0.35
     thine
    -0.35
     thyself
    -0.35
    POSITIVE LOGITS
    Зноскі
    0.66
     ProtoMessage
    0.65
    انگلیسی
    0.64
     nawr
    0.63
    });*/
    0.63
    __'
    0.63
     pages
    0.62
     esternos
    0.61
     Chwiliwch
    0.61
    Література
    0.60
    Activations Density 0.000%

    No Known Activations