© 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. 0-CLT-HP
    7. 94489
    Prev
    Next
    INDEX
    Explanations

    'of'

    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
    Hentet
    -0.50
    tified
    -0.45
    ContentAlignment
    -0.44
    AnchorStyles
    -0.43
     Translated
    -0.42
     Theſe
    -0.42
     getItemId
    -0.41
    摆
    -0.41
     }}=\
    -0.40
     Blon
    -0.40
    POSITIVE LOGITS
     ivelany
    0.79
     ProtoMessage
    0.74
     fieldNum
    0.69
     Italijani
    0.68
    MLLoader
    0.66
    
    0.66
    FailureListener
    0.65
    protoimpl
    0.63
    
    0.63
    েক
    0.62
    Activations Density 0.476%

    No Known Activations