© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91011
    Prev
    Next
    INDEX
    Explanations

    viewing/observation

    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
    View
    -0.91
    view
    -0.58
    tin
    -0.56
    endphp
    -0.53
    t
    -0.48
    d
    -0.48
    حيط
    -0.47
    c
    -0.47
    x
    -0.47
    b
    -0.46
    POSITIVE LOGITS
    OGND
    0.64
    leyebilirsiniz
    0.64
     utafitiHapana
    0.64
    surate
    0.63
    nteral
    0.58
    hicles
    0.56
     Pager
    0.56
     getArguments
    0.55
     hanem
    0.55
    ябре
    0.55
    Activations Density 0.545%

    No Known Activations