© 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. 1-CLT-HP
    7. 13298
    Prev
    Next
    INDEX
    Explanations

    Crow

    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
     Crow
    -0.94
    Crow
    -0.75
     CROW
    -0.67
     crow
    -0.63
    énéral
    -0.58
    ContentAsync
    -0.54
     fratelli
    -0.54
     vectoriales
    -0.53
     tamaños
    -0.53
    cour
    -0.51
    POSITIVE LOGITS
    esModule
    0.63
    ArrowToggle
    0.56
     BioLib
    0.55
    userdetails
    0.54
    InjectMocks
    0.53
    Ecotoxicity
    0.52
     NRW
    0.52
    GoogleApiClient
    0.52
     Waterloo
    0.51
     Bonaparte
    0.51
    Activations Density 1.001%

    No Known Activations