© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38963
    Prev
    Next
    INDEX
    Explanations

    Aly

    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
     Aly
    -1.20
    Aly
    -0.99
    illage
    -0.89
     HEL
    -0.71
    AndEndTag
    -0.69
     beginnetje
    -0.66
    -------
    -0.62
     AssemblyProduct
    -0.60
    قایناق‌لار
    -0.60
    EndContext
    -0.56
    POSITIVE LOGITS
     MediatR
    0.53
     RouterModule
    0.52
    ✭✭
    0.51
    scaleX
    0.51
    RunWith
    0.50
     Widers
    0.49
    rawDesc
    0.48
    m
    0.47
    ToolStrip
    0.47
    ader
    0.46
    Activations Density 0.575%

    No Known Activations