© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2610
    Prev
    Next
    INDEX
    Explanations

    cone

    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
    __(/*!
    -0.69
    eload
    -0.45
    NewUrlParser
    -0.44
    avi
    -0.42
    WriteBarrier
    -0.42
     AssemblyTitle
    -0.42
    ativer
    -0.41
    uen
    -0.41
    CloseOperation
    -0.40
    hus
    -0.40
    POSITIVE LOGITS
    SharedDtor
    0.71
     beginnetje
    0.69
     Riemann
    0.64
     betweenstory
    0.63
     diffe
    0.60
     Weyl
    0.59
     singularities
    0.58
     Galo
    0.58
     umbi
    0.58
     Chrift
    0.57
    Activations Density 0.037%

    No Known Activations