© 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. 1-CLT-HP
    7. 45735
    Prev
    Next
    INDEX
    Explanations

    empty

    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
    empty
    -1.42
     Empty
    -1.41
     empty
    -1.37
     emptied
    -1.35
     emptying
    -1.30
    Empty
    -1.24
     EMPTY
    -1.03
     vazio
    -0.98
    EMPTY
    -0.96
     emptiness
    -0.94
    POSITIVE LOGITS
    ing
    0.54
    envolvimento
    0.50
    ed
    0.48
    edic
    0.47
    +:+
    0.46
    Tradu
    0.45
    ghs
    0.45
    eded
    0.45
    ghouse
    0.44
    addCriterion
    0.44
    Activations Density 0.441%

    No Known Activations