© 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. 94799
    Prev
    Next
    INDEX
    Explanations

    injuries

    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
     injuries
    -1.36
     Injuries
    -1.15
    Injuries
    -1.01
    HasForeignKey
    -0.73
    injured
    -0.73
     IBOutlet
    -0.70
     blessures
    -0.69
    juries
    -0.68
    LookAnd
    -0.67
     casualties
    -0.65
    POSITIVE LOGITS
    ter
    0.59
    nad
    0.58
    ness
    0.58
    nos
    0.52
    にん
    0.52
    man
    0.51
    mith
    0.50
    ting
    0.49
    ly
    0.49
    sy
    0.49
    Activations Density 1.275%

    No Known Activations