© 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. 5-CLT-HP
    7. 4170
    Prev
    Next
    INDEX
    Explanations

    Relatedness

    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
     Waray
    -0.52
    bulos
    -0.48
    ÈRE
    -0.47
     textStatus
    -0.47
     halves
    -0.46
     />);
    -0.44
    PHONY
    -0.43
     strtok
    -0.43
    IEDAD
    -0.43
    illiard
    -0.42
    POSITIVE LOGITS
     مشين
    0.70
     propOrder
    0.63
    oredCriteria
    0.56
     somehow
    0.53
     ruota
    0.52
    (©
    0.51
     disambiguazione
    0.51
    AnchorTagHelper
    0.51
     katanya
    0.50
    Soorten
    0.50
    Activations Density 0.003%

    No Known Activations