© 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. 1-CLT-HP
    7. 11328
    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
    findpost
    -0.49
     matter
    -0.48
    matter
    -0.42
    nell
    -0.41
    бив
    -0.37
    ness
    -0.36
    leness
    -0.36
     MATTER
    -0.35
     مرئيه
    -0.34
     tele
    -0.34
    POSITIVE LOGITS
     referenties
    0.98
    AndEndTag
    0.82
    OrNil
    0.78
    tonode
    0.74
    NameInMap
    0.73
    Xna
    0.73
     AttributeSet
    0.70
    ManyToMany
    0.69
    IMPORTED
    0.67
    исленность
    0.67
    Activations Density 0.010%

    No Known Activations