© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1026
    Prev
    Next
    INDEX
    Explanations

    new species

    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
    PerformLayout
    -0.57
    joba
    -0.52
     hasNext
    -0.52
     newArr
    -0.52
    InvalidProtocol
    -0.51
    VersionUID
    -0.50
    RTLD
    -0.49
    InputTagHelper
    -0.49
     مرئيه
    -0.47
     Dreaming
    -0.47
    POSITIVE LOGITS
     combination
    0.59
    ociação
    0.58
     Nacionales
    0.58
     combinations
    0.58
    combinations
    0.56
     muualla
    0.55
    combination
    0.55
     combinatie
    0.52
     Munster
    0.52
     combinación
    0.52
    Activations Density 0.044%

    No Known Activations