© 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. 2007
    Prev
    Next
    INDEX
    Explanations

    but

    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
     itſelf
    -0.93
     fermés
    -0.76
     ExecuteAsync
    -0.75
     InputDecoration
    -0.73
    tagHelperRunner
    -0.73
     ويكيپيديا
    -0.73
     découver
    -0.71
     TestBed
    -0.71
     mourut
    -0.71
     auroit
    -0.69
    POSITIVE LOGITS
     to
    0.79
     are
    0.76
     do
    0.63
     were
    0.59
     go
    0.48
     honor
    0.46
    ollectionView
    0.46
     result
    0.45
     use
    0.44
     validate
    0.44
    Activations Density 0.007%

    No Known Activations