© 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. 97577
    Prev
    Next
    INDEX
    Explanations

    legal/official communication

    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
     parole
    -0.71
    ssal
    -0.52
     Cent
    -0.52
     tap
    -0.52
     Parole
    -0.51
    andri
    -0.48
    @[+][
    -0.47
    مك
    -0.46
     Vikipedi
    -0.45
     Namen
    -0.45
    POSITIVE LOGITS
    ImageContext
    0.72
     itſelf
    0.71
     '{@
    0.68
     myſelf
    0.68
    URLException
    0.66
    UserScript
    0.65
     EClass
    0.65
     themſelves
    0.62
    heses
    0.61
     bershka
    0.61
    Activations Density 1.731%

    No Known Activations