© 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. 15024
    Prev
    Next
    INDEX
    Explanations

    weight

    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
    Tikang
    -0.77
    Демографія
    -0.65
    ]='\
    -0.63
    ruptedException
    -0.61
    atelli
    -0.61
    coefficients
    -0.60
     recevez
    -0.60
    council
    -0.60
     doGet
    -0.60
    NOWLEDG
    -0.59
    POSITIVE LOGITS
    StoryboardSegue
    0.56
     Chwiliwch
    0.52
    SequentialGroup
    0.50
    complexContent
    0.49
    AnchorStyles
    0.49
     ExecuteAsync
    0.47
    tagext
    0.44
    racuse
    0.44
     TRANS
    0.43
    FXML
    0.42
    Activations Density 0.003%

    No Known Activations