© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41424
    Prev
    Next
    INDEX
    Explanations

    scientific abstracts, questions

    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
    }")
    -0.50
    }}
    -0.46
    </b>
    -0.45
    `
    -0.43
     The
    -0.43
    ");
    -0.43
    "]
    -0.42
     ComVisible
    -0.41
    </h2>
    -0.41
    ")
    -0.41
    POSITIVE LOGITS
     OnInit
    0.77
    providedIn
    0.77
     الرياضيه
    0.76
     Akismet
    0.75
    afficheront
    0.69
     tartalomajánló
    0.69
    issauga
    0.67
    ckeye
    0.67
    bootstrapcdn
    0.67
    atguigu
    0.66
    Activations Density 0.050%

    No Known Activations