© 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. 0-CLT-HP
    7. 40671
    Prev
    Next
    INDEX
    Explanations

    eat

    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
    chism
    -0.66
    tagHelper
    -0.63
     թվական
    -0.61
    ReusableCell
    -0.59
    =$?
    -0.58
    RenderAtEndOf
    -0.57
    örté
    -0.56
    ódz
    -0.56
    cinnati
    -0.56
    utsu
    -0.56
    POSITIVE LOGITS
    ngdoc
    0.54
    TestingModule
    0.53
    XmlAccessorType
    0.53
     odkazy
    0.52
     tetto
    0.46
     ExecuteAsync
    0.45
    Jeografia
    0.45
     kvinna
    0.45
    <bos>
    0.43
    InitVars
    0.43
    Activations Density 0.007%

    No Known Activations