© 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. 388
    Prev
    Next
    INDEX
    Explanations

    flex

    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
     flex
    -1.45
    Flex
    -1.40
     Flex
    -1.32
    flex
    -1.31
    FLEX
    -1.08
     FLEX
    -1.08
     flexing
    -1.01
     flexion
    -0.68
     flexib
    -0.66
    flexible
    -0.62
    POSITIVE LOGITS
    ion
    0.69
    ็จ
    0.68
    ure
    0.60
    ing
    0.59
    itron
    0.58
    ions
    0.57
     <<<<<<<<<<<<<<
    0.55
    ed
    0.55
    ibly
    0.54
    المراجع
    0.54
    Activations Density 0.075%

    No Known Activations