© 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. 96247
    Prev
    Next
    INDEX
    Explanations

    methods or models

    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
    providedIn
    -0.67
     الحره
    -0.63
    NameInMap
    -0.55
    onAttach
    -0.55
     referenties
    -0.55
    omitempty
    -0.54
    riwal
    -0.52
    });
    -0.51
    Демографія
    -0.49
    Erfolge
    -0.48
    POSITIVE LOGITS
    dafx
    0.63
    WriteTagHelper
    0.61
    Geplaatst
    0.61
     snippetHide
    0.59
     réguli
    0.56
     кӀ
    0.55
     of
    0.54
     Gemeinsame
    0.54
     remplacé
    0.52
     juridiques
    0.51
    Activations Density 0.000%

    No Known Activations