© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96073
    Prev
    Next
    INDEX
    Explanations

    the

    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
     themselves
    -0.64
    
    -0.56
    CloseOperation
    -0.56
    __*/
    -0.55
    izr
    -0.54
    themselves
    -0.52
    ITABLE
    -0.52
    thington
    -0.49
     المثال
    -0.49
    ihnachten
    -0.48
    POSITIVE LOGITS
    resave
    0.58
     nocturna
    0.58
     Allociné
    0.57
     espirituales
    0.57
     SYLLABLE
    0.56
     nocturno
    0.54
    RegistryLite
    0.54
    BufferException
    0.52
    principalTable
    0.52
     sagrado
    0.51
    Activations Density 0.003%

    No Known Activations