© 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. 1-CLT-HP
    7. 9462
    Prev
    Next
    INDEX
    Explanations

    ink

    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
    inkling
    -1.45
    ink
    -1.44
    INK
    -1.41
    inkles
    -1.16
    WithIOException
    -1.14
    inking
    -1.08
    inks
    -1.02
    inkled
    -0.99
    inker
    -0.94
    inkle
    -0.89
    POSITIVE LOGITS
    存于互联网档案馆
    0.64
    y
    0.63
    ie
    0.57
    AutoScaleMode
    0.52
    ach
    0.47
    يح
    0.46
    e
    0.46
    י
    0.46
    keh
    0.46
    ed
    0.44
    Activations Density 0.018%

    No Known Activations