© 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. 20-CLT-HP
    7. 77434
    Prev
    Next
    INDEX
    Explanations

    collision/impact

    np_max-act-logits · 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
     дописавши
    -0.87
    setVerticalGroup
    -0.84
     esternos
    -0.82
     GenerationType
    -0.78
     برانيه
    -0.78
     lenker
    -0.76
    oredCriteria
    -0.75
     مرئيه
    -0.74
     ostavi
    -0.74
     يتيمه
    -0.72
    POSITIVE LOGITS
     impact
    0.68
     col
    0.68
     head
    0.65
     ram
    0.64
    Xna
    0.63
     slam
    0.58
     sma
    0.56
     slamming
    0.56
     slammed
    0.55
    col
    0.53
    Activations Density 0.002%

    No Known Activations