© 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. 4-CLT-HP
    7. 1221
    Prev
    Next
    INDEX
    Explanations

    an

    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
     recently
    -0.53
     recent
    -0.51
     som
    -0.48
    少
    -0.46
    гай
    -0.45
     some
    -0.45
    hen
    -0.45
    GeneratedCode
    -0.44
     most
    -0.44
    some
    -0.44
    POSITIVE LOGITS
     tartalomajánló
    0.80
     Theſe
    0.76
     fubject
    0.75
     وتسجيلات
    0.72
     itſelf
    0.71
     Paglinawan
    0.69
    èlement
    0.68
     Portail
    0.68
    ſelves
    0.68
     neceff
    0.67
    Activations Density 0.007%

    No Known Activations