© 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. 20-CLT-HP
    7. 74654
    Prev
    Next
    INDEX
    Explanations

    regulatory

    np_max-act-logits · 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
     snippetHide
    -0.65
     quæ
    -0.62
    ContentAsync
    -0.61
    ⓧ
    -0.57
    Carriera
    -0.57
     avoient
    -0.55
    AdapterFactory
    -0.54
     lèvres
    -0.54
     prieten
    -0.52
     sociaux
    -0.52
    POSITIVE LOGITS
     scheme
    0.77
     regime
    0.62
     schemes
    0.61
    tvguidetime
    0.58
     provision
    0.56
    ंदीखरीदारी
    0.56
     construct
    0.54
    WriteLiteral
    0.53
     schema
    0.53
    %)$
    0.53
    Activations Density 0.001%

    No Known Activations