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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90567
    Prev
    Next
    INDEX
    Explanations

    negatively impacted

    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
     affected
    -0.81
     badly
    -0.61
     severely
    -0.58
     Affected
    -0.56
     damaged
    -0.54
    affected
    -0.52
     most
    -0.48
     greatly
    -0.47
     quite
    -0.46
     harmed
    -0.45
    POSITIVE LOGITS
     الحره
    1.11
    StoryboardSegue
    0.86
    AsUp
    0.78
    Παραπομπές
    0.78
     المعيارى
    0.77
     esternos
    0.77
    Composable
    0.75
    DebuggerNonUser
    0.75
    bolista
    0.75
     LUMP
    0.74
    Activations Density 0.013%

    No Known Activations