© 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. 3877
    Prev
    Next
    INDEX
    Explanations

    in

    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
    PropertyGroup
    -0.47
    than
    -0.46
     imb
    -0.43
    gın
    -0.43
    geç
    -0.42
     Ad
    -0.42
     nearest
    -0.41
     produisons
    -0.41
    zungen
    -0.41
    uticos
    -0.41
    POSITIVE LOGITS
     HasFactory
    0.72
    +#+
    0.65
    ंदीखरीदारी
    0.64
     CreateTagHelper
    0.63
    ButterKnife
    0.63
    urlencoded
    0.61
     MediatR
    0.61
     okhttp
    0.60
    ilever
    0.60
     jsPsych
    0.57
    Activations Density 0.000%

    No Known Activations