© 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. 5-CLT-HP
    7. 91504
    Prev
    Next
    INDEX
    Explanations

    problems

    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
     spread
    -0.60
     Spread
    -0.53
    계
    -0.48
    Spread
    -0.47
    spread
    -0.46
    ريق
    -0.46
     ense
    -0.45
    ToFit
    -0.42
     Valve
    -0.42
     distributed
    -0.42
    POSITIVE LOGITS
    mobileqq
    0.85
    ]")]
    0.72
     فريبيس
    0.68
    ArgsConstructor
    0.67
     estekak
    0.65
    EFIAPI
    0.63
    անում
    0.59
     hospitals
    0.57
    ########.
    0.57
     Италијани
    0.57
    Activations Density 0.001%

    No Known Activations