© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1251
    Prev
    Next
    INDEX
    Explanations

    fear, import, copyright

    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
     незавершена
    -0.68
    igshid
    -0.61
    MigrationBuilder
    -0.51
     Schulte
    -0.51
    Демографія
    -0.50
     Emmett
    -0.50
     représ
    -0.50
    putar
    -0.50
    ubs
    -0.50
     sanitaires
    -0.50
    POSITIVE LOGITS
     lest
    0.81
     nakalista
    0.58
    참고
    0.54
     []).
    0.52
    awtextra
    0.52
    },[])
    0.51
    Autoritní
    0.50
    herin
    0.48
    hatikan
    0.47
    ruptedException
    0.45
    Activations Density 0.025%

    No Known Activations