© 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. 4373
    Prev
    Next
    INDEX
    Explanations

    this

    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
     ujednoznacz
    -0.61
     defies
    -0.53
    #+#
    -0.52
    nodoc
    -0.52
    曖昧さ回避
    -0.48
    áctenos
    -0.47
     acuer
    -0.45
    XmlEnum
    -0.44
    MergeFrom
    -0.43
    Aux
    -0.43
    POSITIVE LOGITS
     InputDecoration
    0.79
     للمعارف
    0.65
     whole
    0.65
    GraphicsUnit
    0.61
     lifetime
    0.61
     Administrativna
    0.60
     entire
    0.57
    GenerationType
    0.56
    inheit
    0.56
     part
    0.55
    Activations Density 0.004%

    No Known Activations