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. 4-CLT-HP
    4. 4138
    Prev
    Next
    INDEX
    Explanations

    Code and URLs

    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
     refusé
    -0.64
     sauvages
    -0.62
     abandonné
    -0.57
    igneurs
    -0.57
     kautta
    -0.56
     commerciaux
    -0.55
     colorés
    -0.55
     humains
    -0.54
    zają
    -0.54
     stället
    -0.53
    POSITIVE LOGITS
     صوتيه
    0.48
    rainian
    0.45
    "]/
    0.45
    ίων
    0.43
    });*/
    0.42
     study
    0.42
     */;
    0.42
     pinulongan
    0.42
    ran
    0.42
     Study
    0.42
    Activations Density 0.005%

    No Known Activations