© 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. 4497
    Prev
    Next
    INDEX
    Explanations

    need

    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
    setVerticalGroup
    -1.24
    OGND
    -1.17
    WebVitals
    -1.09
    __':
    -0.93
    Autoritní
    -0.90
    LookAnd
    -0.86
    __":
    -0.84
    AutoScaleMode
    -0.83
    RectangleBorder
    -0.83
     CreateTagHelper
    -0.83
    POSITIVE LOGITS
     to
    1.11
     additional
    0.61
     be
    0.61
     a
    0.60
     protection
    0.54
     an
    0.53
     access
    0.47
     strong
    0.47
     extensive
    0.47
     direct
    0.47
    Activations Density 0.007%

    No Known Activations