© 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. 0-CLT-HP
    7. 94009
    Prev
    Next
    INDEX
    Explanations

    numbers one and two

    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
    dhan
    -0.83
    arity
    -0.44
     lesson
    -0.43
    ady
    -0.43
    AD
    -0.43
     variable
    -0.42
    Rè
    -0.42
     Volk
    -0.42
     were
    -0.41
    Variable
    -0.41
    POSITIVE LOGITS
    TemporalType
    0.78
    IntoConstraints
    0.77
     Reſ
    0.70
     Anſ
    0.69
     Theſe
    0.69
    ſelves
    0.68
     becauſe
    0.67
     otomatig
    0.67
     ſame
    0.66
     myſelf
    0.66
    Activations Density 0.056%

    No Known Activations