© 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. 20-CLT-HP
    7. 76009
    Prev
    Next
    INDEX
    Explanations

    Relationships between things

    np_max-act-logits · 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
    methods
    -0.74
     Paths
    -0.74
    Methods
    -0.74
     Efq
    -0.73
     methods
    -0.73
    dimensions
    -0.71
    Sides
    -0.71
     approaches
    -0.71
     Methods
    -0.70
     Sides
    -0.70
    POSITIVE LOGITS
    ,
    0.57
     and
    0.53
    amous
    0.43
    えない
    0.42
     an
    0.41
    announced
    0.41
    気になる
    0.40
    ğini
    0.40
    wo
    0.40
     helicópter
    0.40
    Activations Density 0.001%

    No Known Activations