© 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. 38756
    Prev
    Next
    INDEX
    Explanations

    irectional

    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
    irectional
    -0.67
     to
    -0.57
     po
    -0.51
     so
    -0.48
     baik
    -0.47
    ANCED
    -0.47
    self
    -0.46
    bekistan
    -0.46
     bem
    -0.46
    boru
    -0.45
    POSITIVE LOGITS
    RenderAtEndOf
    1.00
     AssemblyVersion
    0.89
     snippetHide
    0.87
    AnchorStyles
    0.84
    ValueStyle
    0.83
     makeStyles
    0.81
     onCreateView
    0.79
     <<<<<<<<<<<<<<
    0.77
     Tread
    0.77
    SourceChecksum
    0.75
    Activations Density 0.185%

    No Known Activations