© 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. 38897
    Prev
    Next
    INDEX
    Explanations

    -ing verbs

    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
     bearing
    -2.05
    bearing
    -1.75
     Bearing
    -1.65
    Bearing
    -1.45
     bearings
    -1.25
     myſelf
    -1.09
     Bearings
    -1.04
     whoſe
    -1.02
     Efq
    -1.02
     itſelf
    -1.00
    POSITIVE LOGITS
    iotensin
    0.60
     b
    0.51
     al
    0.51
     on
    0.51
    >|
    0.47
     ab
    0.46
     power
    0.45
     
    0.45
     emp
    0.44
     vil
    0.44
    Activations Density 0.025%

    No Known Activations