© 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. 1981
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    illoma
    -0.60
     ocurrido
    -0.47
    otá
    -0.45
     Hex
    -0.44
    <bos>
    -0.44
    ITAN
    -0.43
    oporosis
    -0.43
    ộn
    -0.43
     chng
    -0.43
    TAL
    -0.42
    POSITIVE LOGITS
    webElementGuid
    0.57
    complexContent
    0.54
    __*/
    0.54
    StreetMap
    0.53
     rebus
    0.51
    </thead>
    0.51
    dafx
    0.51
    extAlignment
    0.50
     borne
    0.50
     للاسماء
    0.50
    Activations Density 0.006%

    No Known Activations