© 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. 1-CLT-HP
    7. 12391
    Prev
    Next
    INDEX
    Explanations

    places

    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
    teo
    -1.15
    grapher
    -0.76
    elock
    -0.67
    oggles
    -0.61
     Dokter
    -0.60
     &___
    -0.59
    TypedDataSet
    -0.58
     intptr
    -0.57
     ostavi
    -0.53
    PRWEB
    -0.52
    POSITIVE LOGITS
    onViewCreated
    0.60
    StackNavigator
    0.60
     MainAxisSize
    0.60
    EndGlobalSection
    0.57
    Eloquent
    0.56
    BuildContext
    0.53
    formik
    0.50
    resave
    0.49
    complexContent
    0.49
    KURZBESCHREIBUNG
    0.49
    Activations Density 0.049%

    No Known Activations