© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97731
    Prev
    Next
    INDEX
    Explanations

    DT

    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
    DT
    -1.74
    dt
    -1.52
     DT
    -1.42
     dt
    -1.27
    Dt
    -0.87
     Dt
    -0.71
    GEBURTSDATUM
    -0.60
     Faculty
    -0.56
    jects
    -0.52
    dts
    -0.51
    POSITIVE LOGITS
    ArgsConstructor
    0.76
    aarrggbb
    0.74
    WriteTagHelper
    0.71
    gonic
    0.71
     estekak
    0.69
    $}}
    0.66
    ]")]
    0.63
    хьтан
    0.62
    ⓧ
    0.62
    HomeAsUpEnabled
    0.60
    Activations Density 0.560%

    No Known Activations