© 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. 42649
    Prev
    Next
    INDEX
    Explanations

    Track

    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
    Track
    -1.23
    tracking
    -1.23
    track
    -1.20
     trackers
    -1.19
     tracking
    -1.18
    tracked
    -1.17
     Tracking
    -1.16
    Tracking
    -1.15
    TRACK
    -1.13
     Track
    -1.12
    POSITIVE LOGITS
    i
    0.52
    ai
    0.51
    etes
    0.49
    ent
    0.49
    ers
    0.48
    й
    0.47
    ian
    0.47
    uno
    0.46
    اج
    0.45
    ett
    0.45
    Activations Density 0.135%

    No Known Activations