Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73583
    Prev
    Next
    INDEX
    Explanations

    two

    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
     صوتيه
    -0.63
    adə
    -0.62
    ِّف
    -0.62
    ContentAsync
    -0.59
    ScopeManager
    -0.58
    UserScript
    -0.57
     Flur
    -0.55
    VIAF
    -0.55
    enderror
    -0.54
     Baby
    -0.54
    POSITIVE LOGITS
     sub
    0.63
    IntoConstraints
    0.49
     calves
    0.48
    twimg
    0.47
     cow
    0.47
     dependent
    0.46
    NameInMap
    0.46
     joe
    0.43
    usercontent
    0.43
    лтамалар
    0.43
    Activations Density 0.000%

    No Known Activations