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. 4-CLT-HP
    4. 3669
    Prev
    Next
    INDEX
    Explanations

    higherMethod 0: Cannot make any guesses.higher

    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
    viä
    -0.45
     kr
    -0.44
     while
    -0.44
     Pa
    -0.44
     required
    -0.43
    CDCl
    -0.43
    required
    -0.42
     heard
    -0.42
     not
    -0.42
     sekaligus
    -0.41
    POSITIVE LOGITS
     Efq
    1.06
     Houſe
    1.04
     houſe
    1.02
     Majefty
    0.95
     purpoſe
    0.93
     Jefus
    0.90
     fubject
    0.89
     Reſ
    0.89
     laſt
    0.88
     ſtate
    0.88
    Activations Density 0.003%

    No Known Activations