© 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. 0-CLT-HP
    7. 38767
    Prev
    Next
    INDEX
    Explanations

    **************/

    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
    出版年
    -0.49
    orszá
    -0.49
     cser
    -0.48
    rictions
    -0.47
    tableFuture
    -0.45
     due
    -0.44
     szív
    -0.44
     ritrov
    -0.44
     debido
    -0.44
    الدراسه
    -0.44
    POSITIVE LOGITS
     estimés
    0.82
     utafitiHapana
    0.82
    AnchorStyles
    0.68
     ujednoznacz
    0.65
    Portail
    0.63
    кипедия
    0.62
    StructEnd
    0.61
    //
    0.59
    PreferredItem
    0.59
    сылкі
    0.59
    Activations Density 2.046%

    No Known Activations