© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11480
    Prev
    Next
    INDEX
    Explanations

    roads/paths

    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
    paths
    -0.88
     Paths
    -0.85
     paths
    -0.83
     path
    -0.74
    path
    -0.73
     Path
    -0.73
    Path
    -0.71
    Paths
    -0.70
     roads
    -0.68
    PATH
    -0.66
    POSITIVE LOGITS
     Zwie
    0.56
    LookAnd
    0.53
     Viktor
    0.50
    WebElementEntity
    0.50
    enteuer
    0.48
    aula
    0.47
     Lithuanian
    0.47
     információk
    0.47
    ization
    0.46
    artifactId
    0.44
    Activations Density 0.092%

    No Known Activations