© 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. 0-CLT-HP
    7. 91966
    Prev
    Next
    INDEX
    Explanations

    Text

    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
    T
    -1.41
    Text
    -0.92
     T
    -0.82
     Text
    -0.78
    S
    -0.65
    R
    -0.62
    I
    -0.60
    TEXT
    -0.58
    D
    -0.55
    N
    -0.55
    POSITIVE LOGITS
    OGND
    1.07
     виправивши
    1.05
     autorytatywna
    1.03
     FetchType
    1.01
    })*/
    0.98
    Autoritní
    0.96
    Билгалдахарш
    0.96
     дописавши
    0.95
    };*/
    0.94
    RenderAtEndOf
    0.91
    Activations Density 1.489%

    No Known Activations