© 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. 0-CLT-HP
    7. 93870
    Prev
    Next
    INDEX
    Explanations

    small deliveries

    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
     shots
    -0.81
    CrossRef
    -0.80
    shots
    -0.74
     tails
    -0.69
    tails
    -0.68
     heads
    -0.67
    heads
    -0.64
     shift
    -0.60
    tagHelper
    -0.60
    ‍♀️
    -0.60
    POSITIVE LOGITS
     calendriers
    0.54
     of
    0.51
     evicted
    0.51
    Obrázky
    0.50
     sown
    0.50
     sunk
    0.49
     rigged
    0.48
     SEDS
    0.48
     awarded
    0.48
    hips
    0.47
    Activations Density 0.105%

    No Known Activations