© 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. 12474
    Prev
    Next
    INDEX
    Explanations

    Instructions and rules

    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
    mergeFrom
    -0.49
    SBATCH
    -0.46
     PLWABN
    -0.45
    :✨
    -0.44
    клопе
    -0.43
    oredCriteria
    -0.43
     pinulongan
    -0.42
    knex
    -0.42
    SPATH
    -0.42
    "];
    -0.41
    POSITIVE LOGITS
     SwitchCompat
    0.58
     tartalomajánló
    0.57
    addProperty
    0.57
     InputDecoration
    0.53
    npos
    0.53
    FontOfSize
    0.51
    収録曲
    0.51
    divarius
    0.50
    #
    0.50
     vastaan
    0.50
    Activations Density 0.074%

    No Known Activations