© 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. 5471
    Prev
    Next
    INDEX
    Explanations

    +

    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
    setViewportView
    -0.44
    addPreferredGap
    -0.44
    buy
    -0.43
    IRIT
    -0.42
    uality
    -0.41
     Squadron
    -0.40
    Conclusão
    -0.40
    didSet
    -0.40
    Buy
    -0.39
     Bellini
    -0.38
    POSITIVE LOGITS
    Према
    0.74
    IVEREF
    0.71
     Normdatei
    0.69
     ligiloj
    0.61
     TestBed
    0.59
    ьажоргаш
    0.58
    Oph
    0.56
    modes
    0.54
     старости
    0.52
     GenerationType
    0.52
    Activations Density 0.003%

    No Known Activations