© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92081
    Prev
    Next
    INDEX
    Explanations

    sex

    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
     '<?
    -0.77
    abetes
    -0.72
     ansik
    -0.69
     Sexual
    -0.68
     sexual
    -0.67
     Sex
    -0.67
    IBOutlet
    -0.66
     millón
    -0.66
     "<?
    -0.65
     quæ
    -0.65
    POSITIVE LOGITS
     SafeMath
    0.46
    atiable
    0.44
    ChildScrollView
    0.43
    CppMethod
    0.42
     ब्रेकडाउन
    0.40
    eners
    0.39
    quard
    0.39
     greed
    0.39
     ed
    0.38
     raven
    0.38
    Activations Density 0.045%

    No Known Activations