© 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. 72054
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Signalez
    -0.67
     AppModule
    -0.65
     inheritance
    -0.65
    μία
    -0.58
    :]:
    -0.58
    foglal
    -0.57
    valent
    -0.57
     ویکی‌پدیا
    -0.57
    वरण
    -0.56
     ESCAPE
    -0.56
    POSITIVE LOGITS
    úgó
    0.53
     used
    0.51
    клопе
    0.50
    himovic
    0.50
     referrerpolicy
    0.50
     poveznice
    0.48
    ]")]
    0.48
    quiao
    0.46
    NegativeButton
    0.46
    antMatchers
    0.45
    Activations Density 0.001%

    No Known Activations