© 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. 5-CLT-HP
    7. 93793
    Prev
    Next
    INDEX
    Explanations

    6, 7, or 8

    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
    Rüyada
    -0.67
    ########.
    -0.64
     InputDecoration
    -0.60
    Попис
    -0.59
    findpost
    -0.58
    MockBean
    -0.58
    StoryboardSegue
    -0.58
     HasFactory
    -0.57
    ыгана
    -0.55
    Xna
    -0.54
    POSITIVE LOGITS
     a
    0.53
    else
    0.53
    displayquote
    0.50
    :
    0.48
     tonight
    0.47
    </thead>
    0.45
    Tē
    0.45
     nocturna
    0.45
    yet
    0.44
     odpo
    0.44
    Activations Density 0.009%

    No Known Activations