© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39850
    Prev
    Next
    INDEX
    Explanations

    inflater

    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
    findpost
    -0.56
    FTFY
    -0.54
     mergeFrom
    -0.53
     Keuangan
    -0.49
    WithMany
    -0.48
    Quit
    -0.48
     quit
    -0.47
    Herzlich
    -0.46
     nakalista
    -0.45
    IMENTS
    -0.45
    POSITIVE LOGITS
    ParallelGroup
    0.82
    gdx
    0.69
    MENAFN
    0.59
    "]);
    
    0.57
     raiſ
    0.57
     formales
    0.57
    มาะ
    0.57
    |}{
    0.56
     gyhoeddwyd
    0.56
    Hauptartikel
    0.56
    Activations Density 0.236%

    No Known Activations