© 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. 91622
    Prev
    Next
    INDEX
    Explanations

    Players

    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
    bootstrapcdn
    -0.77
    évaluateur
    -0.70
    AddTagHelper
    -0.65
     CreateTagHelper
    -0.63
    webElement
    -0.63
    országban
    -0.63
    ഓ
    -0.62
    UnusedPrivate
    -0.62
    FormTagHelper
    -0.61
    BeginInit
    -0.60
    POSITIVE LOGITS
    DataSnapshot
    0.40
    SignedIn
    0.39
    fif
    0.37
    ↵
    0.37
    protoimpl
    0.37
     >=",
    0.35
    terraform
    0.35
     Played
    0.35
    WithMany
    0.35
     matelas
    0.34
    Activations Density 0.007%

    No Known Activations