© 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. 4193
    Prev
    Next
    INDEX
    Explanations

    Literal and symbolic "heart"

    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
    matchCondition
    -0.73
    yntaxException
    -0.71
    oredCriteria
    -0.70
     typelib
    -0.68
    SharedDtor
    -0.67
    }))
    -0.67
    onOptions
    -0.66
    AddTagHelper
    -0.66
    IUrlHelper
    -0.66
    queryInterface
    -0.65
    POSITIVE LOGITS
    land
    0.63
    lands
    0.48
    LAND
    0.46
     interested
    0.45
    rent
    0.45
    um
    0.44
    stone
    0.44
    巻
    0.41
    landa
    0.41
    rex
    0.40
    Activations Density 0.002%

    No Known Activations