© 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. 38810
    Prev
    Next
    INDEX
    Explanations

    stadiums and measurements

    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
     measured
    -0.65
    henge
    -0.62
    lid
    -0.60
    writeField
    -0.59
    ogaster
    -0.59
    oa̍t
    -0.59
    testi
    -0.58
    发表于
    -0.58
    WriteBarrier
    -0.58
     disambiguazione
    -0.57
    POSITIVE LOGITS
     ourselves
    0.61
     import
    0.57
     yourself
    0.57
     Daven
    0.55
     tanken
    0.55
     themselves
    0.53
    存于互联网档案馆
    0.53
     verm
    0.53
     Ericsson
    0.51
     shortcuts
    0.50
    Activations Density 0.086%

    No Known Activations