© 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. 1-CLT-HP
    7. 9189
    Prev
    Next
    INDEX
    Explanations

    beginnings

    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
    Karakteristik
    -0.54
    #+#
    -0.47
    NamedQueries
    -0.44
    Autoritní
    -0.44
     pájaros
    -0.43
     jSON
    -0.43
    érature
    -0.43
    rativa
    -0.41
     AttributeSet
    -0.41
    достатки
    -0.41
    POSITIVE LOGITS
    tonsoft
    0.75
    jsxFileName
    0.73
    WebVitals
    0.70
     يتيمه
    0.68
    Portale
    0.68
    CppMethod
    0.65
    migrationBuilder
    0.64
     anarch
    0.63
    webElementGuid
    0.59
    CodedInputStream
    0.58
    Activations Density 0.135%

    No Known Activations