© 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. 4-CLT-HP
    7. 1181
    Prev
    Next
    INDEX
    Explanations

    Ctrl key combinations

    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
     
    -0.53
    énagement
    -0.49
    ChildScrollView
    -0.46
     Gymnas
    -0.46
    Jegyzetek
    -0.46
    Kaynakça
    -0.45
    </thead>
    -0.45
    itename
    -0.45
    hatenablog
    -0.45
    utsu
    -0.44
    POSITIVE LOGITS
     Meksiku
    0.62
     alt
    0.58
    hoeddwyd
    0.57
    $_['
    0.57
    estacks
    0.56
    Попис
    0.56
    libft
    0.56
    flow
    0.55
    IntoConstraints
    0.55
    不住
    0.52
    Activations Density 0.005%

    No Known Activations