© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75504
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical docs

    np_max-act-logits · 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
     autorytatywna
    -0.74
    IntoConstraints
    -0.59
    cedo
    -0.58
     oprot
    -0.58
    ='_
    -0.56
    ριο
    -0.53
     getArguments
    -0.53
    Governing
    -0.51
    UnknownFields
    -0.51
    AlterField
    -0.50
    POSITIVE LOGITS
    HideFlags
    0.55
     szóci
    0.54
    Swatch
    0.53
    SceneManagement
    0.49
     AssemblyTitle
    0.49
    Mutagenicity
    0.48
    WebVitals
    0.47
    minder
    0.46
     חיצוניים
    0.44
     ddelweddau
    0.44
    Activations Density 0.001%

    No Known Activations