© 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. 4-CLT-HP
    7. 3378
    Prev
    Next
    INDEX
    Explanations

    XML documents and data

    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
     autorytatywna
    -0.70
    Autoritní
    -0.61
    öte
    -0.59
    multer
    -0.56
    Хьажоргаш
    -0.56
    writerow
    -0.54
    #+#
    -0.54
    DrawerToggle
    -0.53
    messageInfo
    -0.52
    TypedDataSet
    -0.51
    POSITIVE LOGITS
    GEBURTS
    0.59
    WriteTagHelper
    0.55
    </tfoot>
    0.53
    ("/:
    0.52
     виправивши
    0.52
    __':
    0.49
    subsubsection
    0.49
    OSH
    0.49
    ēju
    0.48
    uckleberry
    0.47
    Activations Density 0.000%

    No Known Activations