© 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. 0-CLT-HP
    7. 94331
    Prev
    Next
    INDEX
    Explanations

    matter

    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
     matter
    -1.26
     EnglishChoose
    -0.85
    matter
    -0.84
     matters
    -0.81
     transfieras
    -0.80
    sphere
    -0.78
     sphere
    -0.77
     hemisphere
    -0.77
     محفوظة
    -0.75
     MATTER
    -0.71
    POSITIVE LOGITS
    ,
    0.57
    Personendaten
    0.55
     trans
    0.53
    StoreMessageInfo
    0.51
    /***/
    0.50
    trans
    0.49
     ContentValues
    0.47
    VideoCapture
    0.46
    oflavin
    0.46
    .
    0.46
    Activations Density 0.216%

    No Known Activations