© 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. 4-CLT-HP
    7. 4384
    Prev
    Next
    INDEX
    Explanations

    Problems and solutions

    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
    izop
    -0.47
    леко
    -0.44
    ,
    -0.43
     (
    -0.42
     Left
    -0.41
     and
    -0.41
     paljon
    -0.40
     
    -0.40
     Are
    -0.40
     both
    -0.40
    POSITIVE LOGITS
     Monfieur
    0.93
     Efq
    0.92
    ########.
    0.88
     iſt
    0.79
     betweenstory
    0.78
     $_"
    0.77
     occaf
    0.77
     itſelf
    0.74
     ſtate
    0.74
     Eſ
    0.74
    Activations Density 0.170%

    No Known Activations