© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4632
    Prev
    Next
    INDEX
    Explanations

    Numerical descriptions

    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
     tartalomajánló
    -0.52
    )++;
    -0.51
    Geographie
    -0.51
    Personensuche
    -0.50
    Organisateur
    -0.50
    ktır
    -0.46
     DLC
    -0.46
    ]();
    -0.45
    раздо
    -0.44
     Belong
    -0.44
    POSITIVE LOGITS
    
    0.58
    iettes
    0.57
     ton
    0.55
     Pyramids
    0.53
     tonne
    0.52
     tier
    0.51
    mmate
    0.49
    AndView
    0.49
     levelled
    0.48
     wheeled
    0.48
    Activations Density 0.001%

    No Known Activations