© 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. 44012
    Prev
    Next
    INDEX
    Explanations

    observation, confirmation

    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
     confirmed
    -1.17
     recognised
    -1.15
    confirmed
    -1.15
     documented
    -1.10
     detected
    -1.00
     verified
    -1.00
     Confirmed
    -1.00
     recognized
    -0.99
     otomatig
    -0.97
    webElementXpaths
    -0.96
    POSITIVE LOGITS
     by
    0.90
     in
    0.72
     as
    0.71
     for
    0.64
     with
    0.64
     on
    0.62
     when
    0.58
     individually
    0.57
     through
    0.56
     along
    0.56
    Activations Density 0.053%

    No Known Activations