© 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. 4-CLT-HP
    7. 46
    Prev
    Next
    INDEX
    Explanations

    any

    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
    fromnode
    -0.71
     rischi
    -0.52
     ReactDOM
    -0.52
    detectChanges
    -0.51
     bất
    -0.51
     risques
    -0.51
    lineno
    -0.50
     mêmes
    -0.49
     invokingState
    -0.48
    enk
    -0.48
    POSITIVE LOGITS
     nakalista
    0.66
    //
    0.66
     pieces
    0.62
    maketitle
    0.57
    pieces
    0.57
     medications
    0.57
    :✨
    0.56
     surfaces
    0.55
    AILS
    0.53
     medicines
    0.53
    Activations Density 0.003%

    No Known Activations