© 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. 0-CLT-HP
    7. 38962
    Prev
    Next
    INDEX
    Explanations

    unnecessary

    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
    necessary
    -1.17
     unnecessary
    -1.16
     necessary
    -1.11
     Necessary
    -1.02
    Necessary
    -1.01
     inneces
    -0.95
     Dated
    -0.93
     unnecessarily
    -0.88
     necessária
    -0.86
    ReusableCell
    -0.84
    POSITIVE LOGITS
    ,
    0.44
    /
    0.44
     and
    0.43
    toInt
    0.41
      
    0.41
     influence
    0.40
     or
    0.40
    ?
    0.40
    2
    0.39
    toxicity
    0.39
    Activations Density 0.204%

    No Known Activations