© 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. 20-CLT-HP
    7. 76632
    Prev
    Next
    INDEX
    Explanations

    Prior Art, State of Art

    np_max-act-logits · 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
    ConstraintMaker
    -0.87
     myſelf
    -0.84
     gynhyrchwyd
    -0.84
     AssemblyProduct
    -0.83
    mybatisplus
    -0.82
     Normdatei
    -0.81
     comigo
    -0.79
     محفوظة
    -0.79
    contentLoaded
    -0.79
     Италијани
    -0.78
    POSITIVE LOGITS
     an
    0.59
     are
    0.55
     the
    0.46
     and
    0.42
     ar
    0.41
     (
    0.39
     art
    0.39
    0.38
     +
    0.36
     arte
    0.36
    Activations Density 0.004%
    No Known Activations