© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45720
    Prev
    Next
    INDEX
    Explanations

    chol

    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
     adult
    -0.50
    se
    -0.44
     vain
    -0.43
    sprozess
    -0.42
     general
    -0.42
    kost
    -0.42
    res
    -0.41
     ja
    -0.40
    roek
    -0.39
    sy
    -0.39
    POSITIVE LOGITS
    SourceChecksum
    0.77
     gynhyrchwyd
    0.74
     innehå
    0.66
    fxml
    0.65
     Efq
    0.65
     MyBatis
    0.65
    UnsafeEnabled
    0.64
    IUrlHelper
    0.64
    पया
    0.63
    tanleria
    0.63
    Activations Density 0.010%

    No Known Activations