© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1303
    Prev
    Next
    INDEX
    Explanations

    ible

    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
    ible
    -1.28
    ibility
    -1.00
    IBLE
    -0.93
    lining
    -0.66
    orting
    -0.65
    ibles
    -0.63
    hira
    -0.57
     useNavigate
    -0.57
    orted
    -0.53
    reide
    -0.53
    POSITIVE LOGITS
    WriteTagHelper
    0.71
    TabIndex
    0.71
    AndEndTag
    0.69
    UnusedPrivate
    0.63
    Tē
    0.61
     poussière
    0.61
    MessageOf
    0.59
    webElementXpaths
    0.59
    ocino
    0.58
     chimiques
    0.56
    Activations Density 0.027%

    No Known Activations