© 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. 1-CLT-HP
    7. 15488
    Prev
    Next
    INDEX
    Explanations

    how

    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
     SafeMath
    -0.59
     переписи
    -0.53
     objective
    -0.53
    valget
    -0.52
    Conserv
    -0.52
    __':
    -0.52
    כום
    -0.52
    rimônio
    -0.51
    spyOn
    -0.51
    zepam
    -0.51
    POSITIVE LOGITS
    aulted
    0.58
     MessageBoxIcon
    0.54
    verwijspagina
    0.52
     pretty
    0.50
     useParams
    0.49
    pretty
    0.48
    very
    0.47
     spéciaux
    0.47
    withIdentifier
    0.45
     HasFactory
    0.45
    Activations Density 0.005%

    No Known Activations