© 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. 2183
    Prev
    Next
    INDEX
    Explanations

    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
    complexType
    -0.53
    term
    -0.47
    einander
    -0.46
     ihr
    -0.45
    PopupWindow
    -0.41
    PreAuthorize
    -0.41
    чу
    -0.40
     CURIAM
    -0.40
     expertos
    -0.40
    china
    -0.39
    POSITIVE LOGITS
    verwijspagina
    0.81
    NameInMap
    0.73
     Roskov
    0.63
    ̍t
    0.61
    timmt
    0.60
    InSection
    0.60
    IUrlHelper
    0.59
    elemField
    0.59
     direta
    0.57
     salts
    0.57
    Activations Density 0.002%

    No Known Activations