© 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. 38787
    Prev
    Next
    INDEX
    Explanations

    serum

    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
    roscope
    -0.81
     Majefty
    -0.71
     Efq
    -0.70
     pose
    -0.67
     purpoſe
    -0.67
     posed
    -0.65
     bodem
    -0.64
     Hift
    -0.63
    wiſe
    -0.61
     auroit
    -0.60
    POSITIVE LOGITS
     Италијани
    0.64
     ProtoMessage
    0.60
     للمعارف
    0.59
    EDEFAULT
    0.57
    InjectAttribute
    0.56
     AdapterView
    0.54
     /*#__
    0.51
    XmlEnum
    0.50
    en
    0.50
    ніципа
    0.49
    Activations Density 0.165%

    No Known Activations