© 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. 0-CLT-HP
    7. 93763
    Prev
    Next
    INDEX
    Explanations

    crystalline

    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
     löyty
    -0.73
     löytyy
    -0.72
     dignité
    -0.71
     withstand
    -0.69
     paroisse
    -0.68
     métallique
    -0.67
     afhankelijk
    -0.67
     termica
    -0.66
     pédagogique
    -0.64
     varandra
    -0.63
    POSITIVE LOGITS
     ép
    0.65
    xsi
    0.63
     pri
    0.62
     Roh
    0.62
     Quar
    0.61
    ModelForm
    0.58
    LOR
    0.57
    IndentedString
    0.57
    GroupLayout
    0.56
     Fen
    0.56
    Activations Density 0.058%

    No Known Activations