© 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. 1-CLT-HP
    7. 14425
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    rited
    -0.60
    ChildScrollView
    -0.59
    HandleFunc
    -0.58
    ype
    -0.55
    reve
    -0.55
    OfBirth
    -0.54
    Tracce
    -0.53
    ftc
    -0.52
    paravant
    -0.52
     Sco
    -0.52
    POSITIVE LOGITS
     Roskov
    0.59
     effectually
    0.55
     Numerade
    0.50
     isNameExpr
    0.50
     işte
    0.47
     المعيارى
    0.47
    avimas
    0.47
     AssemblyProduct
    0.46
     Italijani
    0.46
     cometh
    0.46
    Activations Density 0.085%

    No Known Activations