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. 1-CLT-HP
    4. 12627
    Prev
    Next
    INDEX
    Explanations

    science

    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
    Personendaten
    -0.69
    :✨
    -0.68
    basicConfig
    -0.68
    ⓧ
    -0.65
    WebVitals
    -0.65
    приєм
    -0.62
    bootstrapcdn
    -0.60
    Concern
    -0.59
    RenderAtEndOf
    -0.57
    awaiter
    -0.57
    POSITIVE LOGITS
    ppur
    0.47
    onomía
    0.45
     Mag
    0.45
    RTRS
    0.43
     pro
    0.43
     mu
    0.42
     gy
    0.42
     I
    0.41
     تانيه
    0.41
     Mou
    0.40
    Activations Density 0.016%

    No Known Activations