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. 0-CLT-HP
    4. 44675
    Prev
    Next
    INDEX
    Explanations

    Vs and Powers

    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
    wski
    -0.71
    nik
    -0.66
    ness
    -0.65
     Powers
    -0.65
    aire
    -0.63
     Cap
    -0.62
     C
    -0.62
    es
    -0.61
    luk
    -0.60
     d
    -0.60
    POSITIVE LOGITS
     Efq
    0.93
     Jefus
    0.90
     ſeveral
    0.88
     Shakspeare
    0.88
     myſelf
    0.88
     neceff
    0.87
     theſe
    0.85
     purpoſe
    0.85
     ſtate
    0.84
     ejus
    0.83
    Activations Density 1.783%

    No Known Activations