© 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. 93627
    Prev
    Next
    INDEX
    Explanations

    Movement, transfer, or transitions

    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
     passage
    -1.02
    passage
    -0.98
     passing
    -0.98
    passing
    -0.85
    Passing
    -0.82
     Passage
    -0.82
     Passing
    -0.80
    Passage
    -0.73
     passed
    -0.69
     passes
    -0.69
    POSITIVE LOGITS
    rative
    0.65
     âgées
    0.63
     tromper
    0.62
     AssemblyProduct
    0.60
    neuf
    0.60
     Ngb
    0.58
    NgModule
    0.57
     into
    0.56
     négatif
    0.56
     nahilalakip
    0.55
    Activations Density 0.011%

    No Known Activations