© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96484
    Prev
    Next
    INDEX
    Explanations

    that

    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
     unless
    -0.90
     while
    -0.84
     although
    -0.83
     if
    -0.82
     though
    -0.74
     whilst
    -0.70
     when
    -0.70
     whether
    -0.69
     even
    -0.68
     for
    -0.66
    POSITIVE LOGITS
    PhysRevD
    0.57
    volves
    0.57
    tifies
    0.56
    nearby
    0.55
    ]++;
    0.52
    fhir
    0.52
    ffers
    0.52
     siger
    0.51
    zeigt
    0.51
    rites
    0.51
    Activations Density 0.003%

    No Known Activations