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. 20-CLT-HP
    4. 73667
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act-logits · 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
    WebVitals
    -0.51
    inquirer
    -0.47
     biru
    -0.47
    annica
    -0.45
    klima
    -0.44
    NameInMap
    -0.43
     propTypes
    -0.43
     Weimar
    -0.43
    ͡
    -0.43
     tecnológica
    -0.42
    POSITIVE LOGITS
    ########.
    0.79
     betweenstory
    0.76
     disambiguazione
    0.74
    expandindo
    0.72
     ujednoznacz
    0.68
    Rohy
    0.66
    parsedMessage
    0.64
    OrBuilder
    0.64
    iseks
    0.60
     الحره
    0.58
    Activations Density 0.000%

    No Known Activations