© 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. 20-CLT-HP
    7. 77282
    Prev
    Next
    INDEX
    Explanations

    Code/technical writing

    np_max-act-logits · 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
    +#+
    -0.57
    CppMethod
    -0.55
     rospy
    -0.54
     itſelf
    -0.52
    Datuak
    -0.52
    quelize
    -0.51
     bezeichneter
    -0.51
     +%
    -0.49
    onChangeText
    -0.49
     Ochoa
    -0.49
    POSITIVE LOGITS
    EDEFAULT
    0.59
    matchCondition
    0.56
    tvguidetime
    0.56
     насељу
    0.56
    titure
    0.54
     estekak
    0.51
    JsonInclude
    0.51
    enterOuterAlt
    0.51
    PDATE
    0.50
    ruik
    0.50
    Activations Density 0.001%

    No Known Activations