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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1091
    Prev
    Next
    INDEX
    Explanations

    remember

    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
    celes
    -0.57
    complexType
    -0.55
     cadeaux
    -0.52
    ]();
    -0.51
     vœux
    -0.51
     INTERESAR
    -0.50
    évaluateur
    -0.50
     traités
    -0.50
     forgetting
    -0.50
    TagHelper
    -0.50
    POSITIVE LOGITS
    mobileqq
    0.60
     accompany
    0.59
     little
    0.54
    providedIn
    0.54
     travels
    0.54
     marches
    0.54
     составе
    0.54
     tell
    0.53
     well
    0.53
     compare
    0.52
    Activations Density 0.001%

    No Known Activations