© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92380
    Prev
    Next
    INDEX
    Explanations

    programming 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
    المشاركات
    -0.59
    ntä
    -0.58
    adaran
    -0.58
    Initializable
    -0.53
    ότητα
    -0.52
    委員会
    -0.51
    RequestMethod
    -0.51
     Rand
    -0.51
    httphttps
    -0.50
     Familienname
    -0.50
    POSITIVE LOGITS
     CreateTagHelper
    0.79
     PLWABN
    0.61
    kloped
    0.57
     Houſe
    0.56
     Majefty
    0.55
     Perfon
    0.55
     alſo
    0.53
     houſe
    0.53
     yonder
    0.52
    참고
    0.52
    Activations Density 0.016%

    No Known Activations