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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 947
    Prev
    Next
    INDEX
    Explanations

    ejec

    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
     BoxFit
    -0.59
     to
    -0.58
     by
    -0.58
    PDIR
    -0.56
     Alec
    -0.56
     Púb
    -0.53
     múltiple
    -0.53
     Efq
    -0.52
     KeyError
    -0.50
     variational
    -0.50
    POSITIVE LOGITS
    Datuak
    0.65
    ThroughAttribute
    0.63
    MLLoader
    0.61
    UnknownFieldSet
    0.57
    PreferredItem
    0.55
    RTEX
    0.54
    endmodule
    0.54
    ISupport
    0.54
     Réponses
    0.54
    RegistryLite
    0.53
    Activations Density 0.001%

    No Known Activations