© 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. 5-CLT-HP
    7. 4161
    Prev
    Next
    INDEX
    Explanations

    LEGO

    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
    shadowRadius
    -0.58
    authService
    -0.51
    pidou
    -0.50
    PreferredItem
    -0.50
     médicas
    -0.49
     partea
    -0.49
    Història
    -0.47
    veratrol
    -0.47
     OMITBAD
    -0.47
    Referències
    -0.47
    POSITIVE LOGITS
     League
    0.80
    __":
    0.77
    League
    0.70
    __':
    0.66
     Leagues
    0.64
     LEAGUE
    0.62
     Lea
    0.59
    FieldBuilder
    0.59
    ThroughAttribute
    0.56
    league
    0.55
    Activations Density 0.012%

    No Known Activations