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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 97184
    Prev
    Next
    INDEX
    Explanations

    Mixed/miscellaneous content

    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
    ']")
    -0.88
     }}$}
    -0.82
     }}"></
    -0.81
     useAppContext
    -0.79
    ')")
    -0.79
     springfox
    -0.78
    }`)
    -0.77
    ,:);
    -0.77
    ']").
    -0.75
    ValueStyle
    -0.75
    POSITIVE LOGITS
    ↵↵
    1.49
    </b>
    0.54
     what
    0.51
    </strong>
    0.48
    0.45
    Answer
    0.45
    What
    0.45
    .
    0.44
     is
    0.44
    ↵↵↵
    0.44
    Activations Density 0.007%

    No Known Activations