© 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. 5-CLT-HP
    7. 4709
    Prev
    Next
    INDEX
    Explanations

    reasoning

    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
    ########.
    -1.02
    Portale
    -1.01
     intptr
    -0.98
    SourceChecksum
    -0.96
     تضيفلها
    -0.95
     يتيمه
    -0.95
    !")
    -0.94
    StoreMessageInfo
    -0.93
     nakalista
    -0.91
    rungsseite
    -0.91
    POSITIVE LOGITS
     it
    0.81
     I
    0.52
     you
    0.48
     we
    0.47
     the
    0.43
     he
    0.43
     if
    0.43
     no
    0.41
     
    0.41
     whilst
    0.40
    Activations Density 0.038%

    No Known Activations