© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94426
    Prev
    Next
    INDEX
    Explanations

    baseball

    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
     مشين
    -0.50
    Concurrent
    -0.50
    답
    -0.49
     heart
    -0.49
     knife
    -0.48
     réessayer
    -0.47
     Púb
    -0.47
     CreateTagHelper
    -0.47
    Heart
    -0.45
    itaine
    -0.45
    POSITIVE LOGITS
     ProtoMessage
    0.64
    offsetof
    0.61
     GenerationType
    0.57
     kaynağından
    0.56
     صوتيه
    0.56
    ThemeOverlay
    0.53
    providedIn
    0.53
    SharedDtor
    0.52
     newOwner
    0.51
    vierung
    0.47
    Activations Density 0.002%

    No Known Activations