© 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. 1136
    Prev
    Next
    INDEX
    Explanations

    contemporaries

    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
    protoimpl
    -0.91
    Personensuche
    -0.82
     AssemblyTitle
    -0.77
    lint
    -0.76
     Readiness
    -0.74
     incomplète
    -0.73
     Shakspeare
    -0.72
    contentLoaded
    -0.70
     Deity
    -0.69
     Inhabitants
    -0.68
    POSITIVE LOGITS
     AppComponent
    0.55
     makl
    0.53
    viewDidLoad
    0.50
    anadium
    0.47
    setContentView
    0.47
    …
    0.46
     nonatomic
    0.46
    strictEqual
    0.46
     pilot
    0.45
    Toluene
    0.44
    Activations Density 0.036%

    No Known Activations