© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2284
    Prev
    Next
    INDEX
    Explanations

    Modality

    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
    Dichloroethene
    -0.50
     Investigators
    -0.45
    alet
    -0.44
    omys
    -0.44
     Wishing
    -0.43
     FERN
    -0.43
     Fara
    -0.43
     Their
    -0.42
     resourceCulture
    -0.42
    oprecip
    -0.41
    POSITIVE LOGITS
     kasarigan
    0.71
    ViewImports
    0.69
    ContentAsync
    0.66
    DockStyle
    0.66
     surprise
    0.64
     even
    0.63
    AndEndTag
    0.61
    tagHelperRunner
    0.61
    __*/
    0.58
    примеча
    0.57
    Activations Density 0.002%

    No Known Activations