© 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. 5-CLT-HP
    7. 92414
    Prev
    Next
    INDEX
    Explanations

    HTML code

    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
     varandra
    -0.58
    ftagPool
    -0.57
     religieuses
    -0.51
     scolaires
    -0.48
    impôt
    -0.47
    antaine
    -0.46
     gemens
    -0.46
     Administrativna
    -0.45
    Архівовано
    -0.45
     flèche
    -0.45
    POSITIVE LOGITS
    ">//
    0.65
    XMLSchema
    0.61
     CreateTagHelper
    0.59
    حياته
    0.53
    ABE
    0.52
    LookAnd
    0.52
     Nunn
    0.51
     <<<<<<<<<<<<<<
    0.50
    WriteAttribute
    0.50
     Alonzo
    0.50
    Activations Density 0.169%

    No Known Activations