© 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. 39864
    Prev
    Next
    INDEX
    Explanations

    subterranean

    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
    izacao
    -0.70
    igns
    -0.58
    lighter
    -0.57
     fairer
    -0.57
    thâu
    -0.57
    izações
    -0.54
    {}{}
    -0.54
    Pacote
    -0.54
    ddots
    -0.53
    ographed
    -0.52
    POSITIVE LOGITS
    awtextra
    0.82
    PreferredItem
    0.63
    ExtendWith
    0.63
    DockStyle
    0.59
    HasAnnotation
    0.59
    webElementGuid
    0.58
    windowFixed
    0.57
     متعلقه
    0.56
    <tbody>
    0.54
     MonoBehaviour
    0.52
    Activations Density 0.083%

    No Known Activations