© 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. 4-CLT-HP
    7. 388
    Prev
    Next
    INDEX
    Explanations

    quotations

    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
     transfieras
    -0.55
    (!__
    -0.51
     CreateTagHelper
    -0.51
    
    -0.48
    mapStateToProps
    -0.46
    clusal
    -0.45
     mergeFrom
    -0.45
    DataAnnotations
    -0.45
     okru
    -0.44
     diatas
    -0.44
    POSITIVE LOGITS
    '));
    0.66
     he
    0.60
     declares
    0.58
     she
    0.58
    rawDesc
    0.56
     declared
    0.56
    djangoproject
    0.54
    Gön
    0.54
    '))
    0.53
     said
    0.53
    Activations Density 0.013%

    No Known Activations