© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2554
    Prev
    Next
    INDEX
    Explanations

    in

    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
     كومونز
    -0.77
    RectangleBorder
    -0.74
    zzleHttp
    -0.73
     >=",
    -0.73
    Geplaatst
    -0.70
    ConstraintMaker
    -0.70
    contentLoaded
    -0.69
    NameInMap
    -0.66
    ViewImports
    -0.65
    stateProvider
    -0.65
    POSITIVE LOGITS
     combination
    0.66
    combination
    0.53
     planning
    0.53
     two
    0.51
     variety
    0.51
     conjunction
    0.50
     combinations
    0.50
     a
    0.47
     four
    0.45
     three
    0.45
    Activations Density 0.007%

    No Known Activations