© 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. 5-CLT-HP
    4. 2083
    Prev
    Next
    INDEX
    Explanations

    apologies and errors

    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
     يتيمه
    -0.85
     betweenstory
    -0.78
    ArrowToggle
    -0.72
     CreateTagHelper
    -0.68
     gynhyrchwyd
    -0.68
    Spoljašnje
    -0.65
    titleMargin
    -0.63
    Personendaten
    -0.60
     kaarangay
    -0.59
    ezers
    -0.59
    POSITIVE LOGITS
     but
    0.65
    .
    0.59
    ;
    0.54
     <<<<<<<<<<<<<<
    0.50
    modelBuilder
    0.47
    PerformLayout
    0.47
    ?
    0.45
    öll
    0.43
    onOptions
    0.43
     [*]
    0.42
    Activations Density 0.004%

    No Known Activations