© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2148
    Prev
    Next
    INDEX
    Explanations

    stand

    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
    migrationBuilder
    -0.77
    TintMode
    -0.77
    +#+#
    -0.73
    TagMode
    -0.68
    :✨
    -0.66
     bezeichneter
    -0.66
    ConstraintMaker
    -0.66
    ImageContext
    -0.63
    Personendaten
    -0.63
    StructEnd
    -0.63
    POSITIVE LOGITS
     for
    0.57
     side
    0.51
     ready
    0.50
     together
    0.50
     up
    0.49
     united
    0.48
     firm
    0.47
     strong
    0.47
     determined
    0.46
     lado
    0.45
    Activations Density 0.001%

    No Known Activations