© 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. 4-CLT-HP
    7. 415
    Prev
    Next
    INDEX
    Explanations

    to

    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
     of
    -0.60
    IntoConstraints
    -0.58
    endphp
    -0.58
    SupportActionBar
    -0.55
    ModelAdmin
    -0.53
     autorytatywna
    -0.51
    nius
    -0.50
    WEBPACK
    -0.49
    InjectMocks
    -0.49
     about
    -0.48
    POSITIVE LOGITS
    UserScript
    0.72
     صوتيه
    0.70
    adaptiveStyles
    0.60
    
    0.59
     متحده
    0.56
     تانيه
    0.56
    +#+#
    0.55
    webElementGuid
    0.54
    황
    0.53
    ◆◆
    0.53
    Activations Density 0.003%

    No Known Activations