© 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. 96877
    Prev
    Next
    INDEX
    Explanations

    website mentions

    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
    richTextPanel
    -0.55
    mel
    -0.48
    Task
    -0.47
     חיצוניים
    -0.47
     df
    -0.45
    F
    -0.44
    N
    -0.44
    el
    -0.44
     Decke
    -0.43
    ee
    -0.43
    POSITIVE LOGITS
    новниш
    0.65
     getRule
    0.61
    ubre
    0.59
    ientí
    0.58
    ########.
    0.57
    帖最后由
    0.56
     désolés
    0.56
    fycat
    0.55
    ztály
    0.54
    oa̍t
    0.54
    Activations Density 0.010%

    No Known Activations