© 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. 1-CLT-HP
    7. 12138
    Prev
    Next
    INDEX
    Explanations

    of

    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
     kautta
    -0.49
     jól
    -0.47
    ReusableCell
    -0.47
    initializeApp
    -0.47
     nisso
    -0.46
    MethodType
    -0.46
     cser
    -0.46
    ————————————
    -0.46
    tahui
    -0.45
     käytt
    -0.45
    POSITIVE LOGITS
    });*/
    0.61
    |}{}
    0.61
     незавершена
    0.60
     paramInt
    0.59
    detectChanges
    0.57
    SerializedName
    0.57
    SuspendLayout
    0.57
    })*/
    0.56
    FieldNumber
    0.56
    AddHtmlAttribute
    0.55
    Activations Density 0.013%

    No Known Activations