© 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. 91104
    Prev
    Next
    INDEX
    Explanations

    relationships

    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
     their
    -0.90
     themselves
    -0.84
    their
    -0.80
    Their
    -0.75
    themselves
    -0.73
     Their
    -0.72
     loro
    -0.68
     THEIR
    -0.68
     they
    -0.67
     leur
    -0.66
    POSITIVE LOGITS
     Италијани
    0.75
     насељу
    0.70
    fucker
    0.69
    ’
    0.69
    '
    0.67
    estacks
    0.66
    :"-"`
    0.65
     Савезне
    0.65
    calaure
    0.65
     linkovi
    0.64
    Activations Density 0.049%

    No Known Activations