© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 75162
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    np_max-act-logits · 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
     AttributeSet
    -0.56
    #+#
    -0.54
    JNIEnv
    -0.50
    fjspx
    -0.47
    UrlResolution
    -0.47
    listeners
    -0.45
    GEBURTS
    -0.45
    unmodifiable
    -0.45
    __":
    
    -0.44
    
    -0.43
    POSITIVE LOGITS
     للاسماء
    0.57
    poko
    0.55
    <?
    0.54
    oa̍t
    0.53
     pole
    0.52
    __.__
    0.52
    حياتها
    0.51
    lacement
    0.51
    حياته
    0.50
     poles
    0.50
    Activations Density 0.002%

    No Known Activations