© 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. 3508
    Prev
    Next
    INDEX
    Explanations

    always

    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
    orgue
    -0.48
    keyboardType
    -0.44
    TICKET
    -0.42
     sonore
    -0.42
     unmodified
    -0.42
     Schwangerschaft
    -0.42
    beruf
    -0.41
     spiritually
    -0.41
     sonora
    -0.40
     remercier
    -0.40
    POSITIVE LOGITS
     resourceCulture
    0.75
     فريبيس
    0.71
    SequentialGroup
    0.69
    UnknownFields
    0.62
    UnsafeEnabled
    0.60
    AddTagHelper
    0.60
    ThroughAttribute
    0.60
    تقاوى
    0.60
    gdx
    0.59
     архивлан
    0.58
    Activations Density 0.007%

    No Known Activations