Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73949
    Prev
    Next
    INDEX
    Explanations

    Computer code/support text

    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
    ]")]
    -0.68
    ConstraintMaker
    -0.63
     onto
    -0.61
     FetchType
    -0.60
     Италијани
    -0.59
     on
    -0.58
    withIdentifier
    -0.57
     sobre
    -0.54
    ására
    -0.54
    اديم
    -0.54
    POSITIVE LOGITS
     in
    1.07
     kasarigan
    0.59
     Réponses
    0.55
     CreateTagHelper
    0.50
     dalam
    0.50
    ột
    0.48
    TargetException
    0.45
     In
    0.45
     CURIAM
    0.44
     conservé
    0.43
    Activations Density 0.001%

    No Known Activations