© 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. 4-CLT-HP
    7. 1613
    Prev
    Next
    INDEX
    Explanations

    i

    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
     remol
    -0.43
    serde
    -0.36
     AP
    -0.36
    clusal
    -0.36
     perifer
    -0.36
    matur
    -0.36
    дем
    -0.35
    ultur
    -0.35
    स्य
    -0.35
    merksam
    -0.34
    POSITIVE LOGITS
    tagHelperRunner
    0.74
    hoeddwyd
    0.68
     NDEBUG
    0.65
     iota
    0.63
    styleable
    0.63
     Amiens
    0.61
     PeEnEo
    0.60
     Bhd
    0.59
    unknownFields
    0.59
     tetrachloride
    0.58
    Activations Density 0.076%

    No Known Activations