© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 42
    Prev
    Next
    INDEX
    Explanations

    measurements and technical context

    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
    of
    -0.57
    .
    -0.55
    if
    -0.53
    tr
    -0.52
    .,
    -0.52
    c
    -0.51
    se
    -0.51
    ns
    -0.51
    im
    -0.50
    ms
    -0.50
    POSITIVE LOGITS
     المعيارى
    0.86
    ]")]
    0.86
     للاسماء
    0.84
     igång
    0.82
    ]^{-
    0.82
      (
    0.81
     виправивши
    0.79
    ----+
    0.77
    Datuak
    0.75
     bezeichneter
    0.73
    Activations Density 0.038%

    No Known Activations