© 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. 5800
    Prev
    Next
    INDEX
    Explanations

    quotations

    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
    antaranya
    -0.82
    期刊论文
    -0.79
    saraba
    -0.79
    LookAnd
    -0.76
     will
    -0.75
     antaranya
    -0.73
     kaarangay
    -0.73
     propOrder
    -0.70
     can
    -0.69
    seamnă
    -0.69
    POSITIVE LOGITS
    it
    1.18
    the
    1.00
    there
    0.96
    we
    0.96
    if
    0.89
    you
    0.85
    when
    0.74
    our
    0.73
    at
    0.73
    this
    0.71
    Activations Density 0.000%

    No Known Activations