© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 95502
    Prev
    Next
    INDEX
    Explanations

    it

    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
     to
    -0.64
     its
    -0.63
     from
    -0.59
    .
    -0.58
     as
    -0.58
     it
    -0.57
     in
    -0.55
    ,
    -0.55
     for
    -0.53
     on
    -0.51
    POSITIVE LOGITS
    <bos>
    0.82
    ’
    0.82
    تقاوى
    0.81
     ſhall
    0.77
    yntaxException
    0.77
    '
    0.74
    __':
    0.73
     ſhould
    0.73
    homonymie
    0.72
     muſt
    0.72
    Activations Density 0.105%

    No Known Activations