© 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. 4152
    Prev
    Next
    INDEX
    Explanations

    qualifying/explaining language

    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
    </caption>
    -0.76
     الحره
    -0.71
     تضيفلها
    -0.70
    CppMethod
    -0.70
    posedge
    -0.69
     jadx
    -0.69
    StoryboardSegue
    -0.69
    зулта
    -0.69
    CPtr
    -0.68
    HtmlAttribute
    -0.68
    POSITIVE LOGITS
    <bos>
    0.66
    ,
    0.65
    ?
    0.49
    !
    0.46
    -
    0.44
    着的
    0.40
     replacing
    0.35
    ting
    0.35
    .
    0.35
    ted
    0.34
    Activations Density 0.067%

    No Known Activations