© 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. 4939
    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
    ]();
    -0.63
     otomatig
    -0.57
     للاسماء
    -0.56
     auffi
    -0.56
     AssemblyCompany
    -0.56
    ########.
    -0.54
     MERCHANTABILITY
    -0.54
    Panamoan
    -0.54
    Koordinaten
    -0.52
     
    -0.52
    POSITIVE LOGITS
    section
    0.59
    RenderAtEndOf
    0.54
    pillar
    0.54
    stage
    0.53
    InSection
    0.52
    phase
    0.51
    part
    0.50
    point
    0.49
    idea
    0.49
    Step
    0.47
    Activations Density 0.002%

    No Known Activations