© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93803
    Prev
    Next
    INDEX
    Explanations

    colon

    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
    this
    -0.69
    It
    -0.65
    There
    -0.65
    these
    -0.64
    These
    -0.62
    there
    -0.62
    A
    -0.62
    AndEndTag
    -0.60
    An
    -0.60
    This
    -0.59
    POSITIVE LOGITS
    OrEmpty
    0.58
     Efq
    0.50
    :
    0.48
     Савезне
    0.47
    utscher
    0.47
    SPATH
    0.46
    ▻
    0.45
    isei
    0.44
    roscopy
    0.43
    moiselle
    0.43
    Activations Density 0.001%

    No Known Activations