© 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. 97762
    Prev
    Next
    INDEX
    Explanations

    March

    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
     March
    -1.47
    March
    -1.42
     march
    -1.05
    march
    -1.04
     MARCH
    -0.99
     June
    -0.96
     April
    -0.87
    April
    -0.85
    MARCH
    -0.84
     July
    -0.80
    POSITIVE LOGITS
     bezeichneter
    1.06
    URLException
    0.95
     Monfieur
    0.92
     AspNetCore
    0.91
     myſelf
    0.91
    ContentAlignment
    0.90
    manteau
    0.88
    utilisons
    0.85
     ―――――
    0.85
    eseorang
    0.84
    Activations Density 0.164%

    No Known Activations