© 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. 1-CLT-HP
    4. 45774
    Prev
    Next
    INDEX
    Explanations

    code

    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
     that
    -0.58
     legal
    -0.53
     past
    -0.53
     bulk
    -0.53
     like
    -0.53
     when
    -0.53
     second
    -0.51
     last
    -0.51
     say
    -0.49
     average
    -0.48
    POSITIVE LOGITS
    +#+#
    0.87
    ">//
    0.71
    \{\\
    0.71
     tartalomajánló
    0.70
     ویکی‌پدی
    0.69
    DeleteBehavior
    0.68
     تضيفلها
    0.66
    featureID
    0.66
    RUnlock
    0.66
    RenderAtEndOf
    0.65
    Activations Density 0.001%

    No Known Activations