© 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. 4-CLT-HP
    7. 4493
    Prev
    Next
    INDEX
    Explanations

    originally

    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
     виправивши
    -0.61
    󠁢
    -0.55
    testens
    -0.51
     _:
    -0.51
    InputBorder
    -0.50
     jeito
    -0.50
     perpetuity
    -0.49
    icitis
    -0.49
     intptr
    -0.49
    @[+][
    -0.49
    POSITIVE LOGITS
     known
    0.90
     just
    0.72
    ,
    0.71
     only
    0.71
     started
    0.70
     called
    0.69
     developed
    0.66
     introduced
    0.65
     launched
    0.64
     referred
    0.63
    Activations Density 0.005%

    No Known Activations