© 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. 4862
    Prev
    Next
    INDEX
    Explanations

    ice

    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
     AssemblyCulture
    -0.62
    IsMutable
    -0.60
    protoc
    -0.56
    WindowConstants
    -0.55
     linkovi
    -0.53
    ImageContext
    -0.53
    MetaObject
    -0.52
    وران
    -0.52
    AnchorTagHelper
    -0.52
    ti
    -0.52
    POSITIVE LOGITS
    FormTagHelper
    0.52
     seizures
    0.51
    GeneratedCode
    0.51
    Threats
    0.48
     menace
    0.48
     harassment
    0.47
    isEnd
    0.47
     NAL
    0.47
     accretion
    0.47
    Kna
    0.47
    Activations Density 0.000%

    No Known Activations