© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39951
    Prev
    Next
    INDEX
    Explanations

    eliminate

    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
     eliminate
    -0.85
     Eliminate
    -0.84
    izes
    -0.75
     eliminates
    -0.72
     eliminating
    -0.65
    elimin
    -0.60
    ova
    -0.59
    ová
    -0.56
     élimin
    -0.52
    aid
    -0.51
    POSITIVE LOGITS
    StoryboardSegue
    0.78
    zzang
    0.61
     subpo
    0.54
    vably
    0.54
    vinas
    0.54
    ugos
    0.54
    Subviews
    0.54
     utafitiHapana
    0.54
    NewGuid
    0.53
     renormal
    0.53
    Activations Density 0.129%

    No Known Activations