© 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. 0-CLT-HP
    7. 42481
    Prev
    Next
    INDEX
    Explanations

    state

    np_max-act · gemini-2.0-flash

    state

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     state
    -2.59
    state
    -2.33
    State
    -1.77
    STATE
    -1.70
     STATE
    -1.68
     State
    -1.65
     states
    -1.61
     estado
    -1.48
    states
    -1.44
    état
    -1.38
    POSITIVE LOGITS
    .*")]
    0.64
    Bước
    0.60
     الاطلاع
    0.57
     ")";
    0.56
     Duma
    0.53
    gelijk
    0.51
     prosecutor
    0.51
     rhestr
    0.47
    SuppressMessage
    0.47
    Ketua
    0.47
    Activations Density 0.150%

    No Known Activations