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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90490
    Prev
    Next
    INDEX
    Explanations

    one

    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
    ↵
    -0.49
    cosa
    -0.45
    nat
    -0.44
    </i>
    -0.44
    चार
    -0.43
    1
    -0.43
    2
    -0.42
     d
    -0.42
    ub
    -0.40
    d
    -0.40
    POSITIVE LOGITS
    mybatisplus
    1.13
    Geplaatst
    0.86
    Disliked
    0.83
     <=",
    0.82
    Datuak
    0.80
    hoeddwyd
    0.80
     Normdatei
    0.78
    ValueStyle
    0.77
    )))));
    0.77
    Бахар
    0.77
    Activations Density 0.651%

    No Known Activations